找真正的自进化闭环
先看项目改变了什么对象，再看反馈、验证、保留和回滚是否存在。
Projects / 项目索引
哪些 AI Agent 项目真的留下了“被反馈改进过”的证据？
本页不是仓库榜单，而是项目证据地图：先判断系统改了什么、谁验证、是否保留，再进入 model card、源仓库、自动关联论文线索和 review-gated 报告。
686classified GitHub repos
300project cards / 证据卡
98strict evolution candidates
2026-07-04最近活跃项目日期
Reader Path / 先按问题读
先选你的判断任务，再进入完整目录
找可运行的工程线索
优先检查 model card、源仓库、测试或 benchmark，再读 review-gated 报告。
找 2026 当前增长
累计 Star 只是历史可见性；当前阶段价值要看新增 star、push、release 和证据完整度。
找 swarm / harness 进化
关注角色、拓扑、共享状态、验证器和 handoff 是否会随反馈改变。
分组
从代码进化到 Agent 组织进化
进化式代码 / AlphaEvolve 类
4 repos · same mechanism family
LLM 作为优化器
3 repos · same mechanism family
Agent 架构自动搜索
1 repos · same mechanism family
Agent 自进化系统
4 repos · same mechanism family
反思 / 精炼经典范式
2 repos · same mechanism family
安全、评判与数据/模型自进化
3 repos · same mechanism family
声明式 Prompt 优化
1 repos · same mechanism family
多 Agent 协作框架
5 repos · same mechanism family
图式 Agent 编排
2 repos · same mechanism family
AI 软件工程
7 repos · same mechanism family
AutoML / ML 知识驱动
2 repos · same mechanism family
反射式进化搜索
2 repos · same mechanism family
进化式 Prompt/上下文优化
1 repos · same mechanism family
进化式多 Agent 系统
3 repos · same mechanism family
LLM 驱动进化计算
5 repos · same mechanism family
质量多样性优化
1 repos · same mechanism family
经典进化算法框架
3 repos · same mechanism family
AutoML 框架
1 repos · same mechanism family
自进化 Agent 综述
2 repos · same mechanism family
LLM Agent 优化
1 repos · same mechanism family
代码模型与评测
5 repos · same mechanism family
遗传编程
1 repos · same mechanism family
多 Agent 协作平台 (Round 4)
6 repos · same mechanism family
LLM 应用开发平台
5 repos · same mechanism family
Agent 评测基准
12 repos · same mechanism family
LLM 基础设施
5 repos · same mechanism family
Agent Skills / Memory / Harness
179 repos · same mechanism family
Historical star-order signal #065 Lossless Claw Context Management Martian-Engineering/lossless-claw
Historical star-order signal #139 Awesome OpenClaw Plugin Index (rohitg00) rohitg00/awesome-openclaw
Historical star-order signal #146 Sponsio Workflow and Multi-Agent Control Plane SponsioLabs/Sponsio
Production Agent Runtimes With Evolution Substrate
9 repos · same mechanism family
Self-Referential Coding Agents
4 repos · same mechanism family
In-Situ Tool Evolution And Agent Control
5 repos · same mechanism family
Agent 框架 (Round 4)
6 repos · same mechanism family
Agent 研究综述 (Round 4)
3 repos · same mechanism family
Repository Cards
逐项复查：机制、证据、限制
进化式代码优化
openevolve
algorithmicsuperintelligence/openevolve
开源 AlphaEvolve 风格的进化式编码智能体，使用 LLM 生成程序变体、评估打分并选择高分候选持续迭代。
Stars6,500
Forks1000
Updated2026-03-18
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器
数据驱动 Agent 进化
agents
数据中心化的自进化语言智能体框架，强调用数据、环境反馈和智能体编排让 Agent 在任务中持续改进。
Stars5,928
Forks482
Updated2024-09-26
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器智能体编排
反思记忆
reflexion
Reflexion 经典实现，使用语言反思作为“ verbal reinforcement ”，把失败经验写入记忆以改进后续行为。
Stars3,158
Forks306
Updated2025-01-14
LicenseMIT
Python 进化/搜索循环反思记忆反馈-精炼评估器/打分器训练/数据循环
Agent 进化框架
AgentEvolver
面向高效自进化智能体系统的研究实现，核心关注轨迹、经验和评估反馈驱动的 Agent 能力提升。
Stars1,441
Forks167
Updated2026-04-01
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器智能体编排训练/数据循环
反馈精炼
self-refine
Self-Refine 经典实现，用同一个 LLM 生成初稿、生成反馈、再根据反馈迭代精炼，无需训练或强化学习。
Stars805
Forks70
Updated2024-10-04
LicenseApache-2.0
Python 反馈-精炼
代码智能体自进化
SE-Agent
面向代码智能体的自进化框架，通过 Revision、Recombination、Refinement 在多条推理轨迹间交换信息，扩大搜索空间。
Stars274
Forks29
Updated2025-09-23
LicenseMIT
Python 进化/搜索循环评估器/打分器智能体编排
科学代码进化
science-codeevolve
面向科学与算法发现的 CodeEvolve 实现，将 LLM 与遗传算法、岛屿模型、交叉/变异等机制结合。
Stars97
Forks14
Updated2026-04-08
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器
上下文/Prompt 进化
SCOPE
Self-evolving Context Optimization via Prompt Evolution，通过提示词/上下文演化优化 LLM 的任务表现。
Stars77
Forks6
Updated2026-03-26
LicenseMIT
Python 进化/搜索循环
自评判训练
LLM-Self-Judge
围绕多模态推理中模型自评判和无监督自进化的官方实现，关注 judge 信号如何驱动模型/数据改进。
Stars43
Forks1
Updated2026-03-24
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器智能体编排训练/数据循环
安全策略进化
DARWIN
自进化 LLM 越狱/安全研究框架，维护策略池并用检索、过滤、马尔可夫选择、反思和遗传演化扩展攻击策略。
Stars41
Forks4
Updated2026-05-07
LicenseNOASSERTION
Python 进化/搜索循环反思记忆
LLM 作为优化器
OPRO
Google DeepMind 的 OPRO（Optimization by PROmpting），用 LLM 作为优化器，通过进化式 Prompt 迭代搜索更优候选。
Stars2,500
Forks200
Updated2024-01-01
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器LLM-as-Optimizer
进化式 Prompt 优化
OpenELM
CarperAI 的开源进化大模型框架，使用 MAP-Elites 质量多样性算法进化 LLM Prompt 和代码。
Stars1,800
Forks150
Updated2024-01-01
LicenseMIT
Python 进化/搜索循环MAP-Elites质量多样性
Agent 架构自动搜索
ADAS
自动设计智能体系统（ADAS），使用 Meta Agent Search 在代码层面搜索候选 Agent 架构。
Stars1,200
Forks100
Updated2024-01-01
LicenseMIT
Python 进化/搜索循环Meta Agent Search智能体编排
进化式数学发现
FunSearch
Google DeepMind 的 FunSearch，用 LLM + 岛屿模型进化搜索发现数学新知识，首个在数学开放问题上超越人类已知的 LLM 系统。
Stars1,500
Forks130
Updated2024-01-01
LicenseApache-2.0
Python 进化/搜索循环岛屿模型数学发现
多 Agent AutoML
AutoML-Agent
ICML 2025 论文实现，分层管理式 5 Agent 的 AutoML 框架，含 7 状态 FSM + Evol-Instruct 进化 + 代码自动修复。
Stars500
Forks50
Updated2025-01-01
LicenseCC-BY-NC-4.0
Python 智能体编排Evol-InstructAutoML
ML 知识库驱动
CoML
微软研究院的交互式 ML 编程助手，通过知识库驱动的配置推荐和 Jupyter Magic 实现经验积累与迁移。
Stars300
Forks40
Updated2025-01-01
LicenseMIT
Python 反馈-精炼知识库配置迁移
多 Agent 协作框架
MetaGPT
高可见度的多智能体协作框架，Code = SOP(Team) 理念，含 SELA（MCTS+LLM）和 AFlow（ICLR 2025 Oral）线索。
Stars50,000
Forks6000
Updated2026-01-01
LicenseMIT
Python 智能体编排SOP(Team)SELAAFlow
自主 Agent 平台
AutoGPT
GitHub 历史高星标自主 Agent 项目之一，定义了 TAO 循环（Thought-Action-Observation），并演进出平台化形态。
Stars175,000
Forks45000
Updated2026-01-01
LicenseMIT
Python 智能体编排TAO循环Agent平台
多 Agent 协作框架
CrewAI
轻量高性能多 Agent 自动化框架，Crew + Flow 双架构，零依赖独立实现，100k+ 认证开发者。
Stars30,000
Forks4000
Updated2026-01-01
LicenseMIT
Python 智能体编排Crew+Flow零依赖
声明式 Prompt 优化
DSPy
斯坦福 NLP 声明式 LLM 编程框架，将 Prompt 视为可优化参数，含 SIMBA 自我反思优化器和丰富 Teleprompter 家族。
Stars25,000
Forks2000
Updated2026-01-01
LicenseMIT
Python 反馈-精炼Prompt优化SIMBATeleprompter
多 Agent 对话框架
AutoGen
微软多智能体对话框架，基于 Actor 模型的消息传递运行时，支持 Round-Robin/Group Chat/Society of Mind 多种编排。
Stars50,000
Forks6000
Updated2026-01-01
LicenseMIT
Python 智能体编排Actor模型Magentic-One
角色扮演 Agent 框架
CAMEL-AI
较早探索多 Agent 角色扮演对话的框架，含 Critic 在环批评机制和 Self-Instruct 数据生成。
Stars12,000
Forks1300
Updated2026-01-01
LicenseApache-2.0
Python 智能体编排角色扮演Critic在环
图式 Agent 编排
LangGraph
LangChain 的状态化多 Agent 工作流框架，将 Agent 编排建模为有向图，支持循环/分支/并行和状态持久化。
Stars20,000
Forks2500
Updated2026-01-01
LicenseMIT
Python 智能体编排有向图Pregel引擎
软件工程 Agent
SWE-Agent
Princeton NLP 软件工程 Agent，ICLR 2025 Oral，提出 Agent-Computer Interface (ACI)；SWE-bench 结果需按论文和 leaderboard 版本复查。
Stars15,000
Forks1500
Updated2026-01-01
LicenseMIT
Python 反馈-精炼ACI设计SWE-bench
AI 软件开发平台
OpenHands
开源 AI 软件开发平台（原 OpenDevin），AI Agent + 完整开发环境（编辑器/终端/浏览器），55k+ Stars。
Stars55,000
Forks6500
Updated2026-01-01
LicenseMIT
Python 智能体编排Microagent沙箱环境
AI 软件工程师
Devika
开源 AI 软件工程师，多 Agent 流水线（规划→研究→决策→编码→测试→修复），支持 8+ LLM 后端。
Stars22,000
Forks3000
Updated2025-01-01
LicenseMIT
Python 智能体编排多LLM流水线
多 Agent 仿真平台
AgentVerse
清华 OpenBMB 多智能体仿真平台（ACL 2024），双模式（仿真+任务求解），含 Reflection 记忆操作器。
Stars5,000
Forks500
Updated2025-01-01
LicenseApache-2.0
Python 智能体编排涌现行为Reflection
反射式进化搜索
ReEvo
NeurIPS 2024 反射式进化搜索框架，将 LLM 作为语言超启发式（LHHs），通过短期/长期反射机制结合交叉变异实现组合优化算法的自动发现。
Stars500
Forks50
Updated2025-01-01
LicenseMIT
Python 进化/搜索循环反思记忆超启发式组合优化
LLM 驱动算法自动发现
LLaMEA
IEEE TEVC 2025 论文，自称 AlphaEvolve 的完全开源后继者，利用 LLM 自动生成和优化元启发式算法，获 GECCO 2025 银质 Humies 奖。
Stars1,200
Forks100
Updated2025-01-01
LicenseMIT
Python 进化/搜索循环评估器/打分器元启发式算法自动发现
进化式 Prompt 优化
EvoPrompt
ICLR 2024 论文，将进化算法（GA/DE）与 LLM 结合实现离散提示词优化，在 31 个数据集上显著超越人工设计的提示词。
Stars300
Forks30
Updated2024-01-01
LicenseMIT
Python 进化/搜索循环评估器/打分器Prompt优化
进化式多 Agent 系统
EvoAgent
NeurIPS 2024 论文，通过进化算法自动将专家 Agent 扩展为多智能体系统，模拟人类社会的繁衍机制实现从单 Agent 到多 Agent 的自动化扩展。
Stars200
Forks20
Updated2025-01-01
LicenseNOASSERTION
Python 进化/搜索循环智能体编排多Agent生成
自进化 Agent 生态系统
EvoAgentX
面向 LLM Agent 的构建、评估与自动进化开源框架，集成 TextGrad/MIPRO/AFlow/EvoPrompt 等多种进化算法优化 workflow 结构与提示词。
Stars6,800
Forks669
Updated2026-01-01
LicenseMIT
Python 进化/搜索循环智能体编排评估器/打分器反馈-精炼自进化引擎
自进化 Agent 记忆系统
EverOS
面向自进化 Agent 的长期记忆平台，把 EverCore、HyperMem、EverMemBench、EvoAgentBench 和 skills/MCP 集成放进同一条记忆到评测的数据流。
Stars1,000
Forks100
Updated2026-01-01
LicenseApache-2.0
Python 反思记忆智能体编排长期记忆自进化Agent
LLM 引导代码进化
OpenTreeSearch
Genentech 发布的基于 PUCT 树搜索的 LLM 引导代码进化工具，构建在 OpenEvolve 之上，用单超参数替代岛屿模型多超参数。
Stars200
Forks20
Updated2026-01-01
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器树搜索代码进化
质量多样性优化
pyribs
USC ICAROS Lab 的质量多样性（QD）优化库，实现高度模块化的 RIBS 框架，支持 CMA-ME/CMA-MEGA/CMA-MAE 等先进 QD 算法。
Stars800
Forks80
Updated2025-01-01
LicenseMIT
Python 进化/搜索循环评估器/打分器质量多样性MAP-Elites
LLM+EC 交叉综述
LLM4EC
IEEE TEVC 综述论文配套资源库，系统整理 LLM 与 EC 交叉领域研究，划分为 LLM 增强 EA、EA 增强 LLM、LLM 与 EA 协同应用三大方向。
Stars200
Forks20
Updated2025-01-01
LicenseNOASSERTION
Markdown 文献综述LLM+EC进化计算
LLM 驱动算法设计综述
LLM4Opt
ACM Computing Surveys 2025 综述配套资源库，提出 LLM 在算法设计中的四范式分类：LLMaO/LLMaP/LLMaE/LLMaD，收录 300+ 篇论文。
Stars400
Forks40
Updated2025-01-01
LicenseNOASSERTION
Markdown 文献综述LLM-as-Optimizer算法设计
无梯度优化框架
Nevergrad
Meta Research 的 Python 无梯度优化平台，实现 100+ 种优化器的统一接口，含差分进化/CMA-ES/粒子群/贝叶斯优化等，通过 NGOpt 自动选择算法。
Stars4,000
Forks400
Updated2025-01-01
LicenseMIT
Python 进化/搜索循环评估器/打分器无梯度优化NGOpt
经典进化算法框架
DEAP
JMLR 2012 经典进化计算框架，支持 GA/GP/ES/多目标/协同进化等多种范式，以算法显式化、数据结构透明化为设计理念，与 multiprocessing/SCOOP 兼容。
Stars6,000
Forks1200
Updated2025-01-01
LicenseLGPL-3.0
Python 进化/搜索循环评估器/打分器遗传算法遗传编程
经典进化策略
pycma
CMA-ES 官方 Python 参考实现，适用于非凸、病态、多模态和噪声连续优化问题，含边界/约束处理、噪声处理和混合整数优化支持。
Stars1,000
Forks250
Updated2025-01-01
LicenseBSD-3-Clause
Python 进化/搜索循环CMA-ES无导数优化
AutoML 框架
auto-sklearn
Freiburg 大学 AutoML 团队开发的自动化机器学习框架（NeurIPS 2015），结合元学习、贝叶斯优化和自动模型集成实现端到端 ML 流程自动化。
Stars7,500
Forks1000
Updated2025-01-01
LicenseApache-2.0
Python 进化/搜索循环评估器/打分器AutoML贝叶斯优化
自进化 Agent 综述
Self-Evolving-Agents
CharlesQ9/Self-Evolving-Agents
普林斯顿/UIUC/MIT 等联合撰写的自进化 Agent 综述，系统回答 What/When/How/Where to Evolve 四个核心问题，覆盖从模型权重到 Agent 架构的多个进化层次。
Stars300
Forks30
Updated2025-01-01
LicenseNOASSERTION
Markdown 文献综述自进化Agent超级智能
LLM 自改进综述
self-improvement-llm
Stony Brook University 发布的 LLM 自改进系统级综述，提出覆盖数据获取/选择/模型优化/推理优化/自主评估的五组件框架，收录 300+ 篇论文。
Stars200
Forks20
Updated2026-01-01
LicenseNOASSERTION
Markdown 文献综述自改进LLM优化
LLM+EA 交叉综述
LLM-EA-Survey
LLM 与 EA 交叉研究综述论文配套资源库，将论文分为 LLM 用于 EA 和 EA 用于 LLM 两大方向，涵盖 2022-2024 年 100+ 篇重要文献。
Stars300
Forks30
Updated2024-01-01
LicenseNOASSERTION
Markdown 文献综述LLM+EA进化计算
GP+LLM 教学
Tutorial-GP-LLM
MIT ALFA Group 的教学项目，展示如何将 LLM 集成到 GP 进化算子中，扩展 pony_gp 框架实现 LLM 驱动的个体初始化、交叉和变异操作。
Stars50
Forks10
Updated2024-01-01
LicenseNOASSERTION
Python 进化/搜索循环遗传编程LLM算子教学
LLM Agent 优化综述
LLM-Agent-Optimization
YoungDubbyDu/LLM-Agent-Optimization
ACM Computing Surveys 接收论文配套列表，系统探讨 LLM Agent 优化技术，划分为参数驱动/无参数/数据集与基准/应用四大类别，收录 200+ 篇论文。
Stars500
Forks50
Updated2026-01-01
LicenseNOASSERTION
Markdown 文献综述Agent优化参数优化无参数优化
代码 LLM 综述
Awesome-Code-LLM
CodeFuse AI (蚂蚁集团) 维护的代码 LLM 全景资源列表，TMLR 论文配套仓库，涵盖模型架构/预训练/代码推理/评估基准等 8 大类别。
Stars2,000
Forks150
Updated2026-01-01
LicenseNOASSERTION
Markdown 文献综述代码LLM模型架构
Agent 评测基准
AgentBench
清华 THUDM 开发的首个系统性 LLM-as-Agent 评测基准（ICLR 2024），设计 8 个截然不同的评测环境，全面评估规划/推理/工具使用/长程决策能力。
Stars3,000
Forks300
Updated2025-01-01
LicenseApache-2.0
Python 评估器/打分器Agent评测多环境基准
RL 组合优化基准
RL4CO
AI4CO 团队的强化学习组合优化基准框架（KDD 2025），基于 PyTorch 生态，包含 20+ 种前沿模型，支持路由/调度/图问题等多种 CO 任务。
Stars1,200
Forks150
Updated2025-01-01
LicenseMIT
Python 进化/搜索循环评估器/打分器强化学习组合优化
基础模型+组合优化综述
Awesome-FM4CO
AI4CO 团队维护的基础模型驱动的组合优化前沿研究索引，收录 2022-2026 年 200+ 篇论文，从 LLM 解决 CO 和领域 FM 两个维度组织文献。
Stars500
Forks50
Updated2026-01-01
LicenseMIT
Markdown 文献综述基础模型组合优化
AI 软件开发平台
OpenDevin
开源 AI 软件开发平台（原 OpenDevin，现 OpenHands），在 SWE-bench 上达到 77.6% 解决率，被 TikTok/Amazon/Netflix/NVIDIA/Google 等采用。
Stars50,000
Forks6000
Updated2026-01-01
LicenseMIT
Python 智能体编排反馈-精炼SWE-bench软件开发
GP+LLM 代码进化
GP-LLM-Code-Evolution
GP+LLM 融合代码进化综合研究报告，分析遗传编程与大语言模型融合的技术路线，涵盖 LLM 作为遗传算子/优化器/超启发式/进化编码 Agent 等方向。
Stars100
Forks20
Updated2025-01-01
LicenseNOASSERTION
Python 进化/搜索循环遗传编程LLM代码进化
自改进 Agent
future-agi
FutureAGI 自改进 AI Agent 框架，支持 Agent 通过反馈循环持续优化自身行为。
Stars5,200
Forks420
Updated2025-06-01
LicenseApache-2.0
Python 自改进反馈循环Agent 框架
自进化 Agent 综述
awesome-self-evolving-agents
XMUDeepLIT/Awesome-Self-Evolving-Agents
厦门大学 XMUDeepLIT 维护的自进化 Agent 领域论文精选列表，涵盖 Self-Evolving、Self-Improving、Self-Debugging 等方向。
Stars3,800
Forks280
Updated2026-01-15
LicenseCC-BY-4.0
Markdown 综述自进化论文索引
多 Agent 协作框架
ag2
AG2（原 AutoGen）微软开源的多 Agent 对话框架，支持可组合的 Agent 编排、群聊、人机协作和工具集成。
Stars5,200
Forks680
Updated2026-05-20
LicenseApache-2.0
Python 多 Agent对话编排人机协作
多 Agent 协作框架
chatdev
ChatDev 清华 OpenBMB 多智能体协作平台，2.0 版为零代码编排平台，Puppeteer 用 RL 优化 Agent 编排（NeurIPS 2025）。
Stars26,000
Forks3200
Updated2026-01-07
LicenseApache-2.0
Python 多 Agent角色扮演RL 编排
Agent 工具使用
openagents
OpenAgents 开源 Agent 平台，专注于 LLM 工具使用（Tool Use）和函数调用能力。
Stars4,200
Forks410
Updated2025-08-01
LicenseApache-2.0
Python 工具调用函数选择Agent 平台
自主 Agent 框架
superagi
SuperAGI 开源自主 AI Agent 框架，提供丰富的工具生态和 Web UI 管理。
Stars16,000
Forks1900
Updated2025-03-01
LicenseMIT
Python 自主 Agent工具生态Web UI
Agent 框架
phidata
PhiData Agent 框架，内置记忆系统、知识库和工具集成，支持构建生产级 AI Agent。
Stars18,000
Forks2200
Updated2026-05-15
LicenseMIT
Python Agent 框架记忆系统知识库
AI 开发助手
smol-developer
Smol Developer 极简 AI 开发助手，以少量代码展示 AI 辅助开发路径。
Stars14,000
Forks1600
Updated2025-06-01
LicenseMIT
Python 极简 Agent代码生成AI 开发
LLM 应用平台
dify
Dify 开源 LLM 应用开发平台，提供可视化工作流编排、RAG 引擎和 Agent 构建工具。
Stars95,000
Forks14000
Updated2026-05-22
LicenseApache-2.0
Python LLM 平台工作流编排RAG
自主 Agent 平台
agentgpt
AgentGPT 浏览器内自主 AI Agent 平台，通过思考→执行→学习循环自动达成目标。
Stars33,000
Forks9100
Updated2025-08-01
LicenseMIT
TypeScript 自主 Agent任务分解Web UI
LLM 评测平台
agenta
Agenta 开源 LLMOps 评测平台，集成 Prompt 管理、系统化评估和可观测性。
Stars8,000
Forks850
Updated2026-05-10
LicenseMIT
Python LLMOps评测框架Prompt 管理
代码执行沙箱
e2b
E2B 开源 AI 代码安全执行沙箱，基于 Firecracker 微虚拟机实现毫秒级启动的隔离环境。
Stars7,000
Forks450
Updated2026-05-18
LicenseMIT
Python 沙箱代码执行安全隔离
自托管 AI 平台
open-webui
Open WebUI 124K+ stars 自托管 AI 平台，支持 Ollama/OpenAI API、内置 RAG、Python 工具插件。
Stars124,000
Forks15000
Updated2026-05-22
LicenseMIT
Python 自托管多 LLMRAG插件
Agent CLI Auto-Memory and Skills
Gemini CLI Auto Memory
Gemini CLI 是 Google 开源终端 AI Agent；Auto Memory 路线把历史会话挖掘成可审核的 durable memory 和 Agent Skills 草稿。
Stars105,000
Forks13900
Updated2026-05-25
LicenseApache-2.0
TypeScript CLI AgentGoogle GeminiMCPagent memoryskills
工作流自动化
n8n
n8n 开源工作流自动化平台，支持 400+ 集成和 AI Agent 节点，可视化编排自动化流程。
Stars75,000
Forks8000
Updated2026-05-22
LicenseSustainable Use
TypeScript 工作流自动化AI Agent
可视化 Agent 平台
langflow
Langflow LangChain 生态的可视化 Agent/工作流构建器，拖拽式设计 LangChain 应用。
Stars58,000
Forks6100
Updated2026-05-20
LicenseMIT
Python 可视化LangChain拖拽构建
Agent 研究综述
awesome-agent-papers
luo-junyu/Awesome-Agent-Papers
Awesome Agent Papers 是 LLM Agent 研究论文精选列表，用于持续追踪 Agent 领域进展。
Stars1,200
Forks100
Updated2026-03-01
LicenseMIT
Markdown 论文索引Agent 研究
Agent 评测基准
swe-bench
SWE-bench 软件工程评测基准，使用真实 GitHub Issue 评估 LLM 生成补丁的能力。
Stars2,800
Forks420
Updated2026-04-01
LicenseMIT
Python 评测基准软件工程代码补丁
Agent 评测基准
osworld
OSWorld 桌面级 OS Agent 评测基准，在真实操作系统环境中评估 AI Agent 的端到端任务完成能力。
Stars2,200
Forks180
Updated2025-12-01
LicenseMIT
Python 评测基准OS 操作端到端
Agent 评测基准
webarena
WebArena Web Agent 评测基准，在真实网站环境中评估 Agent 的网页交互任务完成能力。
Stars2,800
Forks260
Updated2025-10-01
LicenseMIT
Python 评测基准Web 交互浏览器
LLM 基础设施
litellm
LiteLLM 统一 LLM 网关，提供 100+ LLM 提供商的统一接口，支持 Python SDK 和代理服务器。
Stars22,000
Forks2800
Updated2026-05-22
LicenseMIT
Python LLM 网关统一接口代理
LLM 基础设施
ollama
Ollama 140K+ stars 本地 LLM 推理运行时，支持 Llama、Gemma、Mistral 等模型的一键部署。
Stars140,000
Forks11000
Updated2026-05-22
LicenseMIT
Go LLM 推理本地部署模型管理
可视化 LLM 平台
flowise
Flowise 拖拽式 LLM 可视化构建器，通过 UI 拖拽构建 LLM 应用链。
Stars36,000
Forks4500
Updated2026-05-15
LicenseApache-2.0
TypeScript 可视化拖拽构建LLM 链
自主 Agent 框架
babyagi
BabyAGI 任务驱动自主 Agent，通过目标分解、优先级排序和自我反馈循环自动完成复杂任务。
Stars21,000
Forks2900
Updated2024-06-01
LicenseMIT
Python 自主 Agent任务分解自反馈
AI 聊天框架
cheshire-cat
Cheshire Cat AI 模块化聊天框架，通过插件系统实现可扩展的 AI 对话能力。
Stars3,200
Forks380
Updated2026-05-10
LicenseGPL-3.0
Python 插件系统模块化聊天框架
Agent 框架
smolagents
smolagents HuggingFace 轻量级 Agent 框架，简洁 API 构建 AI Agent。
Stars15,000
Forks1300
Updated2026-05-20
LicenseApache-2.0
Python 轻量 AgentHuggingFace工具调用
LLM 应用平台
bisheng
Bisheng 开源 LLM 应用开发平台（毕昇），提供可视化编排、知识库管理和 RAG 引擎。
Stars8,000
Forks1300
Updated2026-05-18
LicenseApache-2.0
Python LLM 平台可视化编排RAG
LLM 聊天框架
chainlit
Chainlit LLM 聊天应用框架，快速构建类似 ChatGPT 的 LLM 应用界面。
Stars10,000
Forks1200
Updated2026-05-15
LicenseApache-2.0
Python 聊天 UILLM 应用快速构建
Agent 评测基准
WildClawBench
WildClawBench 是面向 LLM Agent 的真实世界风格评测基准，强调动态、多轮、长程任务与 anti-overfitting 评估设计。
Stars408
Forks37
Updated2026-05-26
LicenseMIT
Python 评测基准真实任务multi-turnanti-overfitting
Agent 研究综述
awesome-ai-agents-2026
Zijian-Ni/awesome-ai-agents-2026
Awesome AI Agents 2026 精选列表，追踪 2026 年先进 AI Agent 项目和基准。
Stars800
Forks80
Updated2026-05-20
LicenseCC-BY-4.0
Markdown 综述2026 Agent项目追踪
Agent Memory Resource Index
Awesome Agent Memory by cxxz
A curated agent-memory resource index that helps separate memory tools, patterns and research signals from runtime claims.
Stars11
Forks3
Updated2026-05-25
LicenseMIT
Markdown agent memoryresearch indextaxonomy
Git-like Agent Auto-Memory
Memoir
Memoir frames agent memory as declarative, hierarchical and Git-like, making memory state inspectable through commits and branches instead of only vector retrieval.
Stars549
Forks35
Updated2026-05-25
LicenseApache-2.0
Python agent memoryversioned memorycontinuity
Graph-Based Agent Memory Index
Awesome GraphMemory
DEEP-PolyU/Awesome-GraphMemory
Awesome GraphMemory is a paper-facing index for graph-based agent memory, giving the corpus a bridge from memory substrates to graph knowledge structures.
Stars273
Forks15
Updated2026-05-25
LicenseUnknown
Markdown graph memoryagent memorypaper index
Agent Continuity Evaluation
ATANT
ATANT adds an agent-continuity evaluation angle: memory is not only retrieval quality, but whether an agent maintains narrative state and checkpoint continuity.
Stars3
Forks0
Updated2026-05-25
LicenseLicense visible
Python agent continuityevaluationmemory benchmark
Git-Native Agent Framework
Gitagent
Gitagent treats an agent as a Git repository: identity, rules, memory, tools, skills, hooks, plugins and audit state all live in version-controlled files.
Stars404
Forks82
Updated2026-05-25
LicenseMIT
TypeScript git-native agentagent memoryskillsaudit
Agent Skill Evaluation Harness
Skillgrade Agent Skill Evaluation
Skillgrade turns Agent Skills into testable assets with repeatable smoke, reliability and regression trials across Gemini, Claude, Codex, ACP and OpenCode-style agents.
Stars490
Forks35
Updated2026-05-26
LicenseMIT
TypeScript agent skillsevaluationbenchmarkquality gate
Reviewed Web API Agent Skills
Webmaxru Agent Skills
Webmaxru Agent Skills is a reviewed Web API skills collection with explicit creation, validation, remediation and install-check phases.
Stars29
Forks2
Updated2026-05-26
LicensePublic repository license visible
TypeScript / JavaScript agent skillsweb APIsvalidationskill lifecycle
Waza Agent Skill Evaluation CLI
Waza
Waza is Microsoft's Go CLI / framework for agent skills: it scaffolds skills and eval suites, runs benchmark tasks, compares models, checks coverage, and turns SKILL.md assets into measurable quality gates.
Stars904
Forks49
Updated2026-05-26
LicenseMIT
Go agent skillsevaluationbenchmarkquality gate
NEXO Agent Memory Runtime
NEXO Brain
NEXO Brain is a local shared-brain memory runtime for Claude Code, Codex, Claude Desktop and MCP clients, combining persistent memory, RAG, temporal recall, forgetting, trust scoring, benchmark reporting and background self-improvement jobs.
Stars22
Forks9
Updated2026-05-26
LicenseOpen source public repository
Python / MCP agent memoryMCPLoCoMoself-improvement
state-trace Agent Memory Engine
state-trace
state-trace is a graph-native memory engine for AI agents that stores typed memories and causal links, then retrieves state-aware context through graph traversal instead of only vector similarity.
Stars1
Forks0
Updated2026-05-26
LicensePublic repository license not verified
Python agent memorygraph memorystateful agents
Agent Memory Technique Cookbook
Agent Memory Techniques
NirDiamant/Agent_Memory_Techniques
Agent Memory Techniques is a runnable notebook cookbook for 30 LLM-agent memory patterns, covering short-term buffers, long-term stores, cognitive architectures, multi-agent shared memory, framework integrations, LoCoMo-style evaluation and production patterns.
Stars412
Forks58
Updated2026-05-26
LicenseApache-2.0
Jupyter Notebook / Python agent memorycookbookLoCoMoknowledge graphproduction patterns
Agent Harness Benchmark CLI
kbench
kbench normalizes SWE, Terminal-Bench 2.0, tau-bench and Standardized Agent Exams through one CLI and harness contract, including Codex, Claude Code, Gemini CLI, kode-agent-sdk and custom adapter paths.
Stars10
Forks1
Updated2026-05-26
LicenseApache-2.0
TypeScript / Python agent harnessbenchmarkSWE-benchterminal-benchSAE
Smart Contract Agent Benchmark Harness
evmbench
evmbench is a domain-specific benchmark and harness for LLM agents that find and exploit smart-contract bugs, wrapping Codex detect-mode workers, job queues, secret handling, result validation and a report UI.
Stars421
Forks62
Updated2026-05-26
LicenseApache-2.0
TypeScript / Python agent benchmarksecuritycodexsmart contractssandbox
Agent Skill Authoring Methodology
Skills Best Practices
Skills Best Practices is a methodology layer for professional-grade agent skills, emphasizing discoverable frontmatter, progressive disclosure, deterministic helper scripts and LLM-based validation loops.
Stars1,900
Forks131
Updated2026-05-24
Licensenot verified
Python / Markdown agent skillsskill authoringprogressive disclosurevalidationskillgrade
Self-Improving Coding Agent
SICA Self-Improving Coding Agent
MaximeRobeyns/self_improving_coding_agent
SICA is a self-improving coding-agent implementation where the agent works on its own codebase, making it a core self-referential improvement artifact.
Stars324
Forks56
Updated2026-05-26
LicenseMIT
Python self-improving coding agentSICAcode self-modificationICLR 2025 workshop
Autonomous Agent Runtime
Agent Zero
Agent Zero is an autonomous-agent runtime with Linux execution, memory, browser automation, skills, plugins, projects and subordinate agents.
Stars17,600
Forks3600
Updated2026-05-26
LicensePublic repository license visible
Python agent runtimememoryskillsmulti-agentbrowser automation
Autonomous Agent Framework
elizaOS
elizaOS is a high-adoption autonomous-agent framework whose plugin and lifecycle surface can host memory, skill, workflow and evaluator loops.
Stars17,300
Forks5400
Updated2026-05-26
LicenseMIT
TypeScript agent frameworkpluginsautonomous agentsruntime infrastructure
Secure Team Agent Runtime
Centaur
Centaur is a multiplayer self-hosted secure team-agent runtime with Kubernetes sandboxes, bring-your-own harness support, durable workflows, tools and credential boundaries.
Stars469
Forks55
Updated2026-05-26
LicenseView license / MIT signal from public site
Python / TypeScript team agent runtimeharnessdurable workflowscredential boundariessandbox
In-Situ Self-Evolving Agent System
Yunjue Agent
Yunjue Agent is a reproducible zero-start in-situ self-evolving agent system that turns execution feedback into reusable tools and auditable traces.
Stars426
Forks49
Updated2026-02-11
LicenseApache-2.0
Python in-situ self-evolutiontool evolutionbenchmark tracesreproducibilityopen-ended tasks
OpenClaw Self-Evolving Skill
self-evolving-agent
RangeKing/self-evolving-agent is an OpenClaw skill that upgrades self-improvement logs into a governed evolution workspace with curriculum, evals and promotion.
Stars9
Forks0
Updated2026-05-26
LicenseMIT
Python agent skillOpenClawcurriculumevaluationpromotion
Elixir/OTP Self-Evolving Agent Runtime
NexAgent
NexAgent uses Elixir/OTP supervision to combine persistent sessions, memory, dynamic tools, skills, cron, subagents and source-level self-improvement.
Stars64
Forks5
Updated2026-05-26
LicenseUnknown
Elixir self-evolving runtimeElixir/OTPpersistent memorysubagentscode upgrades
Memory and Skill Self-Improvement Toolkit
hermes2anti
hermes2anti is a compact Hermes-inspired memory and skill loop that persists lessons, creates reusable skills, scans them, and recalls prior sessions.
Stars4
Forks0
Updated2026-05-26
LicenseMIT
Python memoryskillsHermes Agentsecurity scanningsession recall
Coding-Agent Control Plane
ADHDev
ADHDev is a self-hosted control plane for long-running coding-agent sessions across IDEs and CLIs, including Codex, Claude Code and Hermes Agent.
Stars33
Forks8
Updated2026-05-26
LicenseAGPL-3.0
TypeScript control planecoding agentssession dashboardCodexClaude Code
Agent Research Skill Library
AI Research SKILLs
Orchestra-Research/AI-research-SKILLs
AI Research SKILLs is a large open-source skill library for turning coding agents into AI research agents across ideation, experiments, evaluation and paper writing.
Stars8,900
Forks679
Updated2026-05-26
LicenseMIT
Markdown skillsautoresearchevaluationpaper writingagent workflow
Agent Process Skill Library
ai-skills
ai-skills is a compact behavioral skill library for coding agents, distributing process discipline across Codex, Claude Code, Cursor, Gemini CLI and related runtimes.
Stars13
Forks3
Updated2026-05-16
LicenseMIT
Shell skillsverificationdebuggingplanningmulti-agent orchestration
Domain Agent Skill Workflow Pack
Claude Trading Skills
agiprolabs/claude-trading-skills
Claude Trading Skills packages trading, DeFi and quantitative finance procedures as reusable Agent Skills for Claude Code, Codex, Cursor, Gemini CLI and other compatible runtimes.
Stars31
Forks14
Updated2026-05-26
LicenseMIT
Python agent skillsdomain workflowtradingCodexClaude Code
Spec-Driven Agent Workflow Skills
Spec Kit Agent Skills
speckit-agent-skills maps Spec Kit methodology into shared skills, prompts, commands and agent files for Claude Code, Codex CLI, GitHub Copilot CLI, Gemini CLI and related runtimes.
Stars88
Forks21
Updated2026-05-26
LicenseAGPL-3.0
Shell agent skillsspec-driven developmentworkflow orchestrationCodexGemini CLI
Enterprise Generalist Agent Harness
CUGA Agent
CUGA is an enterprise generalist agent harness that wires APIs, MCP servers, policies, memory, knowledge and agent skills into configurable web/API task execution.
Stars742
Forks132
Updated2026-05-26
LicenseOpen source public repository
Python agent harnessMCPpolicyskillsenterprise agents
Human-Centered Research Harness
AutoR
AutoR is a terminal-first research harness where AI handles execution, humans retain direction, and every run is stored as an inspectable artifact on disk.
Stars897
Forks22
Updated2026-05-26
LicensePublic repository license not verified
Python research agentharnessartifact-backed runshuman approval
AI-Human Collaboration Harness
Chorus
Chorus is an AI-human collaboration harness that manages session lifecycle, task state, sub-agent orchestration, permissions, observability and failure recovery around LLM agents.
Stars909
Forks84
Updated2026-05-26
LicenseAGPL-3.0
TypeScript agent harnessmulti-agentAI-DLCpermissionsobservability
Enterprise Decision Agent Harness
KWeaver Core
KWeaver Core is a harness-first foundation for enterprise decision agents, combining governed context, knowledge networks, tool policies and TraceAI-style feedback evidence.
Stars803
Forks92
Updated2026-05-26
LicenseApache-2.0
Go decision agentsharnessknowledge networkTraceAIgovernance
Live OpenClaw Benchmark Harness
ClawProBench
ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading, profile selection and repeated-trial reliability.
Stars690
Forks50
Updated2026-05-26
LicenseApache-2.0
Python benchmarkOpenClawagent evaluationdeterministic grading
Claude Code Harness Safety Runtime
sd0x-dev-flow
sd0x-dev-flow is a harness layer for Claude Code with dual-review gates, state-machine controls and fail-closed safety for coding-agent workflows.
Stars157
Forks21
Updated2026-05-26
LicenseMIT
TypeScript harnessClaude Codesafety gatesskill orchestrationagent workflow
Event-Driven Agent Harness Runtime
Utah
Utah is a universally triggered agent harness built on Inngest events with durable retries and local worker execution for think-act-observe loops.
Stars116
Forks2
Updated2026-05-26
LicenseApache-2.0
TypeScript harnessevent-drivenInngestagent memoryskills
Benchmark-Driven Harness Evolution Toolkit
Meta Harness
Meta Harness is a benchmark-driven outer loop for coding-agent harness optimization, with reproducible candidate ledgers and run evidence.
Stars102
Forks11
Updated2026-05-26
LicenseRepository LICENSE file
Python benchmark harnessCodex CLIOllamaproposal ledgeragent optimization
Open AI Memory Infrastructure
Supermemory
Supermemory 是开源 AI memory 基础设施，把聊天与浏览上下文沉淀为可检索、可复用的长期记忆层。
Stars22,700
Forks2100
Updated2026-05-26
LicenseMIT
TypeScript memory substrateretrievalpersonalizationagent memoryinfra
Open Agent Skill Registry
FlagoS Skills
FlagoS skills 提供开源 AI agent 技能注册表和包格式，把技能资产变成可发布、可安装、可复用模块。
Stars12
Forks11
Updated2026-05-26
LicenseApache-2.0
Python skillsregistrypackage formatagent toolingreuse
Agent Skills Benchmark Harness
SkillsBench
SkillsBench evaluates how well AI agents actually use reusable skills across specialized multi-step workflows under deterministic and gym-style benchmark settings.
Stars1,300
Forks312
Updated2026-06-03
LicenseApache-2.0
Python skillsbenchmarkevaluationtask taxonomydataset
Meta-harness framework and reference experiments
Meta-Harness (Stanford IRIS)
stanford-iris-lab/meta-harness
Meta-Harness provides reference code for automated search over model harnesses, including terminal benchmark scaffold evolution and text-classification memory-system search.
Stars1,201
Forks116
Updated2026-04-29
LicenseMIT
Python meta-harnessharness engineeringagent evolutionbenchmarkouter-loop search
Hermes Benchmark Outer-Loop Harness
Hermes Benchmark Outer-Loop Harness
howdymary/hermes-agent-metaharness
Hermes Agent Meta-Harness is a standalone outer-loop evaluator that optimizes Hermes benchmark harness candidates without modifying model weights.
Stars89
Forks9
Updated2026-05-26
LicenseMIT
Python hermesmeta-harnessbenchmark orchestrationfrontier trackingcandidate mutation
Automated Agent Skill KB Construction
SkillX
SkillX is a paper-backed framework that automatically constructs reusable multi-level skill knowledge bases for agents from execution experience.
Stars181
Forks16
Updated2026-05-26
LicenseMIT
Python skillsknowledge baseexperience learningagent transferbenchmark
Persistent Memory Layer for Multi-Agent Runtimes
mem9
mem9 provides a persistent memory server and plugin integrations so multiple agent runtimes can share durable context instead of isolated session notes.
Stars1,100
Forks111
Updated2026-05-27
LicenseApache-2.0
Go memorymulti-agentopenclawcodexpersistent context
OpenClaw Long-Term Memory Plugin
memory-lancedb-pro
CortexReach/memory-lancedb-pro
memory-lancedb-pro is a production-grade OpenClaw memory plugin that combines long-term storage, hybrid retrieval, and scoped context injection for agent workflows.
Stars4,400
Forks725
Updated2026-05-27
LicenseMIT
TypeScript memory pluginlancedbopenclawhybrid retrievalagent context
Agent Company Brain and Memory OS
GBrain
GBrain is an opinionated long-term brain layer for OpenClaw and Hermes-style agents, combining structured memory pages, graph linking, and retrieval workflows.
Stars19,200
Forks2700
Updated2026-05-27
LicenseMIT
TypeScript memory substrateknowledge graphopenclawhermesagent ops
Local-First Agent Passport Memory Bundle
Akephalos
Akephalos is a markdown-first local passport for AI agents that carries durable user and project context across different tools and machines.
Stars0
Forks1
Updated2026-05-27
LicenseMIT
TypeScript local-firstagent passportmemory portabilitymarkdownmcp
Autonomous Scientific Discovery Agent Framework
InternAgent-1.5
InternAgent-1.5 is a unified multi-agent framework for long-horizon autonomous scientific discovery, spanning discovery runs, QA deep research, and reproducible task execution.
Stars1,300
Forks116
Updated2026-05-27
LicenseApache-2.0
Python research agentscientific discoverymulti-agentbenchmarkmemory
OpenClaw Long-Term Memory Module
ClawXMemory
ClawXMemory is a multi-level OpenClaw memory plugin that writes durable file-based long-term memory and performs model-guided recall for project/user context.
Stars33
Forks8
Updated2026-05-27
LicenseMIT
TypeScript memoryopenclawmarkdown memorylong-term contextlocal-first
LLM Computer Harness Runtime
HexAgent
HexAgent is a harness runtime that gives LLM agents an isolated computer layer and pluggable execution protocol instead of coupling agent runtime and machine state.
Stars122
Forks12
Updated2026-05-27
LicenseMIT
Python harnessruntimemcpskillssandbox
Cross-Provider Agent Harness Adapter
Agent Harness (EvalOps)
evalops/agent-harness is a lightweight harness adapter that lets one tool registry and one prompt surface run across OpenAI and Claude agent SDK backends.
Stars18
Forks5
Updated2026-06-04
LicenseMIT
Python harnessprovider swapevaluationmcppythonframework-runtime
Agent Reliability Evaluation Framework
Harness Evals
Harness Evals is an open-source evaluation framework for LLM agents, prompts, and structured outputs with normalized score semantics.
Stars3
Forks3
Updated2026-05-27
LicenseApache-2.0
Python benchmarkevaluationreliabilityagent metricsobservability
Self-Healing Browser Agent Harness
Browser Harness
Browser Harness connects LLM agents to a real browser through a thin editable CDP harness and explicitly encourages runtime self-healing by letting the agent write missing helper code during execution.
Stars14,300
Forks1300
Updated2026-05-20
LicenseMIT
Python browser harnesscdpself-healingplaywrightagent workspace
Cross-Platform Agent Skill Index
Awesome Agent Skills
junminhong/awesome-agent-skills
junminhong/awesome-agent-skills curates reusable skill workflows and templates for Codex, Claude Code, and other agent platforms.
Stars13
Forks7
Updated2026-05-27
LicenseMIT
Markdown skillsresource-indexcodexclaude-codeworkflow templates
Cognitive Workspace Agent Runtime
Trellis
Trellis is an open-source cognitive workspace for autonomous agents with browser execution, persistent workspace memory, and explicit reasoning workflows.
Stars8,500
Forks466
Updated2026-05-27
LicenseAGPL-3.0
Python agent workspacememorybrowser automationplannerruntime
Awesome Agent Harness Landscape
Awesome Agent Harness (Picrew)
Picrew/awesome-agent-harness is a curated index of AI agent harness frameworks, benchmark suites, and reliability-oriented evaluation resources.
Stars673
Forks53
Updated2026-05-27
LicenseUnknown
Markdown harnessawesome-listbenchmarkevaluationresource-index
Harness Curation and Reading Map
Awesome Agent Harness (AutoJunjie)
AutoJunjie/awesome-agent-harness
AutoJunjie/awesome-agent-harness curates the emerging agent harness ecosystem, combining benchmark references and implementation pointers.
Stars437
Forks32
Updated2026-05-27
LicenseUnknown
Markdown harnessresource-indexbenchmarkmemoryprotocols
Claude Code Skill Learning Curriculum
Learn Claude Code
learn-claude-code provides a staged curriculum and practical exercises for Claude Code users to build reliable agent coding workflows.
Stars63,000
Forks10300
Updated2026-05-27
LicenseMIT
Markdown claude-codeskillscurriculumworkflowcoding-agent
Multi-Domain Agent Benchmark Pack
AI Agent Benchmark
murataslan1/ai-agent-benchmark
ai-agent-benchmark is a compact benchmark repository that evaluates AI agents across coding, math, memory, translation, and safety-oriented task slices.
Stars24
Forks4
Updated2026-05-27
LicenseMIT
Markdown benchmarkagent-evaluationmulti-domainsafetycomparison
Long-Horizon Agent Environment
holaOS
holaOS is an agent environment focused on long-horizon continuity, context retention, and self-evolving workflows for autonomous execution.
Stars5,400
Forks328
Updated2026-05-27
LicenseModified Apache-2.0
TypeScript agent oslong-horizonmemorycontextself-evolving
Batteries-included Agent Harness Runtime
Deep Agents
Deep Agents is a batteries-included agent harness that bundles planning, context management, skills, and persistent memory for long-horizon execution.
Stars23,400
Forks3300
Updated2026-05-28
LicenseMIT
Python harnessruntimeskillsmemoryevaluation
Deterministic AI Coding Harness Builder
Archon
Archon is an open-source harness builder for AI coding that turns development processes into deterministic, reusable workflows.
Stars21,900
Forks3300
Updated2026-05-28
LicenseMIT
TypeScript harnessworkflow-enginecoding-agentvalidationorchestration
Ranked Agent Harness Landscape Index
Best of Agent Harnesses
RyanAlberts/best-of-Agent-Harnesses
best-of-Agent-Harnesses curates and ranks 100+ agent harness projects, exposing weekly-updated use-case, eval, memory, MCP, and orchestration comparisons for harness selection.
Stars64
Forks4
Updated2026-05-28
LicenseCC-BY-SA-4.0
Python awesome-listharnessrankingresource-indexevaluation
Self-Evolving Agent Skill Optimizer
SkillOpt
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
Stars4,000
Forks416
Updated2026-05-31
LicenseMIT
Python agent skillsskill optimizationfrozen modelvalidation gatescross-harness eval
Local Long-Term Agent Memory Substrate
TencentDB Agent Memory
Tencent/TencentDB-Agent-Memory
TencentDB Agent Memory provides a local-first long-term memory pipeline for AI agents with plugin integration and benchmarked efficiency gains.
Stars4,300
Forks354
Updated2026-05-28
LicenseMIT
TypeScript memorylong-term-memoryopenclawlocal-firstplugin
Repo-Level Code Agent Benchmark Harness
GitTaskBench
GitTaskBench is a repository-level benchmark for real-world coding-agent tasks from repository understanding through implementation and task delivery.
Stars255
Forks20
Updated2026-05-28
LicenseUnknown
Python benchmarkcode-agentrepo-levelevaluationharness
OpenClaw Package Catalog and Skill Distribution Hub
OpenClaw ClawHub
ClawHub is the OpenClaw package catalog for discovering, rating, and sharing open-source AI coding agent packages and workflows.
Stars8,800
Forks1400
Updated2026-05-28
LicenseMIT
TypeScript openclawpackage-catalogskillsdistributionmarketplace
OpenClaw Skill and Agent Workflow Index
Awesome OpenClaw Skills
VoltAgent/awesome-openclaw-skills
awesome-openclaw-skills is a large curated index of OpenClaw skills, prompts, and reusable agent workflow assets.
Stars49,400
Forks4800
Updated2026-05-28
LicenseMIT
Markdown openclawskillsawesome-listresource-indexcatalog
OpenClaw Community Landscape and Resources
Awesome OpenClaw
awesome-openclaw curates OpenClaw ecosystem resources including skills, runtime guidance, and adjacent project links.
Stars71
Forks11
Updated2026-05-28
LicenseUnknown
Markdown openclawawesome-listskillsonboardingresources
Quantitative Agent Harness Runtime
QuantClaw
QuantClaw is an autonomous quantitative agent runtime built around OpenClaw-style agent workflows for market analysis and execution tasks.
Stars31
Forks5
Updated2026-05-28
LicenseApache-2.0
C++ agent-runtimequantitativeframeworkworkflow-automationtrading
Scientific Agent Skill and Tooling Index
Awesome Scientific Skills
InternScience/Awesome-Scientific-Skills
Awesome-Scientific-Skills is a curated list of scientific-agent skills, tools, and workflows intended for reusable research automation.
Stars400
Forks23
Updated2026-05-28
LicenseMIT
Markdown scientific-agentskillsresource-indexresearch-workflowbenchmark
Open-Ended Agent Benchmark Harness
ClawBench
ClawBench is an open-ended agent benchmark built for evaluating long-horizon OpenClaw-style agent performance and generalization.
Stars338
Forks21
Updated2026-05-28
LicenseApache-2.0
Python benchmarkopen-endedopenclawevaluationagent-harness
Agent Memory Runtime and Context Service
Redis Agent Memory Server
agent-memory-server is Redis-maintained memory middleware that gives AI agents fast, persistent, and flexible context memory through an MCP-compatible service and client stack.
Stars266
Forks50
Updated2026-04-16
LicenseMIT
Python memoryredismcpagent-runtimecontext-service
Memory-Aware Agent Workflow and Evaluation App
LangChain Memory Agent
memory-agent is LangChain’s reference memory-aware agent application that demonstrates persistent user context and long-term adaptive behavior.
Stars1,800
Forks51
Updated2026-05-28
LicenseMIT
TypeScript memorylanggraphlangmemagent-workflowevaluation
Agent Skill Registry and Open Runtime Platform
iFLYTEK SkillHub
SkillHub is an open-source AI agent platform focused on skill packaging, orchestration, and reusable execution components.
Stars3,200
Forks443
Updated2026-05-28
LicenseApache-2.0
C++ skillagent-platformmulti-agentorchestrationruntime
Agent Skill Memory Layer and Runtime Context Engine
Acontext
Acontext provides an agent memory layer designed to persist and retrieve skill-aware context for autonomous AI workflows.
Stars3,500
Forks319
Updated2026-05-28
LicenseApache-2.0
TypeScript memoryagent-skillscontext-engineruntimelong-term-memory
Episodic Agent Memory Substrate and Knowledge Store
Nemori
Nemori is an episodic memory and persistent context engine for autonomous agents that need durable recall across sessions.
Stars202
Forks17
Updated2026-05-28
LicenseMIT
TypeScript memoryepisodicknowledge-graphcontext-retrievalagent-state
Execution-Intent Memory Benchmark Harness
Continuity Benchmarks
Alienfader/continuity-benchmarks
continuity-benchmarks provides reproducible execution-intent memory benchmarks for long-horizon AI coding agents with LongMemEval-S and ID-RAG matrix evaluation.
Stars3
Forks0
Updated2026-05-29
LicenseMIT
TypeScript benchmarkmemorylongmemevalagent-harnessevaluation
Persistent Agent Memory Substrate
MemWeave
memweave is a zero-infrastructure async Python memory library for AI agents using markdown files and SQLite-backed searchable persistence.
Stars39
Forks2
Updated2026-05-29
LicenseMIT
Python agent memorymarkdown memorysqlitehybrid retrievalopenclaw
Procedural Memory Retrieval Benchmark
Procedural Memory Benchmark
Proced_mem_bench benchmarks procedural memory retrieval for language agents across ALFWorld trajectories and upcoming OSWorld scenarios.
Stars6
Forks3
Updated2026-05-29
LicenseApache-2.0
Python benchmarkprocedural-memoryretrievalalfworldosworld
Repository-Scale Agent Translation Benchmark
RepoMod Bench
mcode-benchmark (RepoMod-Bench) evaluates repository-scale AI agent translation across languages and frameworks with hidden test validation.
Stars1
Forks0
Updated2026-05-29
LicenseApache-2.0
Python benchmarkrepo-translationcode-agentspytestevaluation
Enterprise-Scale Coding Agent Benchmark Harness
CodeScaleBench
CodeScaleBench is a benchmark suite for measuring coding agents with external retrieval tools on large enterprise-scale software tasks.
Stars25
Forks3
Updated2026-05-29
LicenseApache-2.0
Python benchmarkcoding-agentharnessmcpenterprise-codebase
Model Safety Benchmark and Reporting Framework
MLCommons ModelBench
MLCommons modelbench runs safety benchmarks against AI models and publishes detailed hazard-oriented benchmark reports.
Stars126
Forks28
Updated2026-05-29
LicenseApache-2.0
Python benchmarksafetymodel-evaluationmlcommonsreporting
Self-Improving Coding Agent Loop
Self-Improving Agent
self-improving-agent studies whether coding agents can improve themselves through a repeated eval-and-update loop over real tasks.
Stars5
Forks0
Updated2026-05-29
LicenseMIT
TypeScript self-improving-agentcoding-agentevolution-loopgithub-actionsautonomous-iteration
Agent Skill Security Resource Index
Awesome Agent Skills Security
LLMSecurity/awesome-agent-skills-security
awesome-agent-skills-security curates security and benchmark resources specifically for agent skill systems and tool-use workflows.
Stars8
Forks9
Updated2026-05-29
LicenseCC0-1.0
Markdown agent-skillssecuritybenchmarkresource-indexllm-security
Agent CLI Orchestration Resource Index
Awesome Agent CLIs
awesome-agent-clis tracks command-line agent tools and workflow utilities that can be reused as skill and harness building blocks.
Stars223
Forks26
Updated2026-05-29
LicenseCC0-1.0
Markdown agent-cliworkflowdeveloper-toolsskill-catalogresource-index
Reusable Agent Skill Library
Agent Skills
agent-skills provides reusable operational skill bundles designed to be installed and maintained across agent runtimes.
Stars7
Forks0
Updated2026-05-29
LicenseMIT
HTML agent-skillsskill-libraryplaybooksworkflowreuse
Persistent Agent Memory Runtime
Agent Memory
agent-memory is an opinionated TypeScript memory runtime focused on extracting, storing, and retrieving long-lived context for AI agents.
Stars5
Forks2
Updated2026-05-29
LicenseUnspecified
TypeScript agent-memorytypescriptredismemory-runtimecontext-persistence
Provenance-Aware Memory Benchmark Framework
Tiermem
Tiermem introduces benchmark tasks that jointly evaluate memory answer quality and provenance consistency for long-term AI assistants.
Stars5
Forks1
Updated2026-05-29
LicenseMIT
Python benchmarkmemoryprovenanceevaluationlong-context
Cross-Platform Agent Skills Resource Index
Awesome Agent Skills (itgoyo)
itgoyo/awesome-agent-skills is a cross-runtime skills index covering Claude Code, Codex, Gemini CLI, Cline, Cursor and MCP-oriented skill resources.
Stars112
Forks10
Updated2026-05-29
LicenseCC-BY-4.0 (README declared)
Markdown agent-skillsresource-indexmcpworkflowcross-runtime
Runtime Agent Skill Loader
Agent Skill Loader
agent-skill-loader provides a TypeScript loader pipeline for wiring reusable skill modules into AI agent runtimes.
Stars10
Forks3
Updated2026-05-29
LicenseMIT
TypeScript agent-skillsskill-loadertypescriptruntimeorchestration
Self-Evolving Agent Design Benchmark
SEAD
SEAD is a benchmark for evaluating LLM-based agents on software system design tasks with an explicit self-evolving-agent framing.
Stars20
Forks1
Updated2026-05-29
LicenseApache-2.0
Python benchmarkself-evolving-agentsystem-designevaluationllm-agent
Mobile Agent Self-Evolution Framework
Darwin Mobile Agent
ai-agents-2030/darwin-mobile-agent
darwin-mobile-agent targets self-evolving mobile automation agents with an explicit iterative improvement workflow.
Stars10
Forks0
Updated2026-05-29
LicenseApache-2.0
Python mobile-agentself-evolutionandroidagent-runtimeevaluation
Long-Term Memory Benchmark Suite
Mem-Gallery
Mem-Gallery provides a benchmark suite for long-term memory capability in LLM-based agents and assistants.
Stars36
Forks2
Updated2026-05-29
LicenseMIT
Python memorybenchmarklong-term-memoryevaluationagent
Framework for Self-Improving Agent Loops
InfiAgent
InfiAgent presents an open-source framework aimed at self-improving AI agent loops with planner/executor/reflection style workflows.
Stars1,900
Forks235
Updated2026-05-29
LicenseMIT
Python self-improving-agentframeworkworkflowreflectionpython
Maintainer Codex Harness for Issue Clusters
Clownfish
clownfish is OpenClaw's maintainer codex harness focused on resolving issue clusters at scale with auditable workflows.
Stars36
Forks11
Updated2026-05-29
LicenseUnspecified (public page metadata)
JavaScript harnessmaintainer-codexissue-clusteringopenclawagent-workflow
OpenClaw Plugin Compatibility Testbed
Crabpot
crabpot is a compatibility testbed repository for OpenClaw community plugins and plugin seam validation.
Stars9
Forks8
Updated2026-05-29
LicenseMIT
JavaScript plugin-compatibilityopenclawharnessevaluationextensions
Local-First GitHub Crawl and Archive Harness
Gitcrawl
gitcrawl is a local-first issue and pull-request crawler for creating reusable repository archives used by maintainer and agent workflows.
Stars76
Forks15
Updated2026-05-29
LicenseMIT
Go github-crawlerlocal-firstgoarchiveharness-tooling
Shared Crawl Infrastructure Toolkit
Crawlkit
crawlkit is OpenClaw's shared Go infrastructure for local-first crawler and archive processing workflows.
Stars33
Forks5
Updated2026-05-29
LicenseMIT
Go crawlkitgotoolkitarchiveopenclaw
Discord Archive and Memory Ingest Harness
Discrawl
discrawl is a Discord CLI crawler with SQLite-backed archival pipelines for building reusable organizational memory datasets.
Stars761
Forks81
Updated2026-05-29
LicenseMIT
Go discord-crawlermemory-ingestsqlitegoopenclaw
Hosted Agent Memory Runtime Plugin
MemOS Cloud OpenClaw Plugin
MemTensor/MemOS-Cloud-OpenClaw-Plugin
MemOS-Cloud-OpenClaw-Plugin is an official OpenClaw plugin that adds hosted long-term memory retrieval and persistence through MemOS Cloud.
Stars367
Forks56
Updated2026-05-29
LicenseApache-2.0
JavaScript memosopenclaw-pluginmemory-runtimelong-term-memorycloud-memory
Experimental Multi-Agent Orchestration Framework
OpenAI Swarm
Swarm is OpenAI’s educational multi-agent orchestration framework for lightweight handoffs, routines, and inspectable agent workflow patterns, now explicitly positioned as a predecessor to the OpenAI Agents SDK.
Stars21,600
Forks2300
Updated2026-04-15
LicenseMIT
Python multi-agentorchestrationhandoffopenaieducational
Reinforcement-Learning Agent Training Framework
Agent Lightning
Agent Lightning is Microsoft's framework for turning arbitrary agent execution traces into RL-friendly transitions and optimizing agent behavior with LightningRL.
Stars17,300
Forks1500
Updated2026-05-29
LicenseMIT
Python reinforcement-learningagent-trainingself-improvementmicrosoftevolution
Cross-Agent Skill Index and Install Guide
Awesome AI Agent Skills
awesome-ai-agent-skills curates reusable skill packs and installation paths across Codex, Claude, Cursor, Gemini CLI, OpenCode, and related agent runtimes.
Stars92
Forks17
Updated2026-05-29
LicenseMIT
Markdown skillsawesome-listcross-agentcodexclaude-code
State-Preserving Agent Runtime and Session Handoff
ACPX
acpx is OpenClaw's state-preserving runtime for switching across coding agents while retaining full session context and ACP compatibility.
Stars2,800
Forks272
Updated2026-05-29
LicenseMIT
TypeScript openclawacpstateful-runtimeskill-orchestrationsession-handoff
Browser Agent Benchmark and Evaluation Harness
Crabbox
crabbox is OpenClaw's browser-agent benchmark framework for reproducible task execution and evaluator-driven comparison.
Stars539
Forks61
Updated2026-05-29
LicenseMIT
Go openclawbenchmarkbrowser-agentevaluationharness
Windows Companion Runtime for Agent Execution
OpenClaw Windows Node
openclaw/openclaw-windows-node
openclaw-windows-node provides a Windows companion runtime layer to execute OpenClaw agent workflows in native Windows contexts.
Stars542
Forks95
Updated2026-05-29
LicenseMIT
C# openclawwindowsruntimecompanion-nodecross-platform
Open Multi-Agent Runtime and Benchmark Harness
Oh My Agent
oh-my-agent is an open source multi-agent AI framework with workflow orchestration, memory modules, tooling integration, and built-in benchmark surfaces.
Stars1,000
Forks118
Updated2026-05-30
LicenseMIT
Python multi-agentworkflowharnessbenchmarkframework
Long-Term Agent Memory and Context Compression Framework
ReMe
ReMe is a memory management toolkit for AI agents that provides long-term memory retention, context compression, and benchmark-backed retrieval quality signals.
Stars3,000
Forks248
Updated2026-05-30
LicenseApache-2.0
Python memorycontext-compressionlong-term-memorybenchmarkagentscope
Portable Agent Memory Interoperability Standard
Open Memory Specification (OMS)
OMS defines a portable and auditable memory standard for autonomous agents, including a binary memory grain format and context assembly language.
Stars5
Forks0
Updated2026-05-30
LicenseCC0-1.0
Markdown memoryinteroperabilityspecificationcalsml
Hierarchical Agent Memory Framework
MemToMem
memtomem provides a hierarchical long-term memory framework to improve context retention, retrieval quality, and continuity in autonomous agent workflows.
Stars5
Forks24
Updated2026-05-30
LicenseApache-2.0
Python memoryhierarchical-memorygraph-memoryagent-runtimepython
Cross-Framework Agent Skills Registry
Awesome Agent Skills (Skillmatic)
skillmatic-ai/awesome-agent-skills
skillmatic-awesome-agent-skills is a large cross-framework directory of reusable agent skills spanning Codex, Claude Code, Cursor, Gemini, and other runtimes.
Stars1,000
Forks98
Updated2026-05-30
LicenseCC0-1.0
Markdown skillsawesome-listcodexclaude-codecursor
Python Agent Workflow Testing Harness
Agentic Harness
agentic-harness is a Python package for building and testing AI workflows with composable harness primitives and lightweight runtime checks.
Stars2
Forks0
Updated2026-05-30
LicenseMIT
Python harnessworkflowpythontestingharness
Cross-IDE .NET Agent Skills Runtime Pack
.NET Skills
dotnet/skills curates production-grade coding-agent skill packs with .NET-focused workflows, scoring guidance, and multi-runtime installation support.
Stars3,200
Forks236
Updated2026-05-30
LicenseMIT
Markdown skillsdotnetcsharpagent-runtimeskill-pack
Composable Agent Skills Pack and Runtime Recipes
Datalayer Agent Skills
datalayer/agent-skills provides composable skill packs and runtime recipes for coding agents with an emphasis on reproducible installation and workflow reuse.
Stars9
Forks1
Updated2026-05-30
LicenseBSD-3-Clause
Python skillsclaude-codecodexworkflowruntime
Enterprise Agent Skills and Playbook Library
Agent Skills (Block)
block/agent-skills is a public enterprise-oriented skill library that packages repeatable coding-agent playbooks for safer and faster software delivery.
Stars96
Forks25
Updated2026-05-30
LicenseApache-2.0
Markdown skillsenterpriseplaybookclaudecodex
Agent Evaluation Harness and Regression Pipeline
EvalMonkey
EvalMonkey provides a lightweight evaluation harness for LLM agents with regression workflows and reusable benchmark checks.
Stars36
Forks4
Updated2026-05-30
LicenseApache-2.0
Python evaluationbenchmarkharnessregressionagent
Agentic Context Engineering Benchmark Suite
AEC Bench
aec-bench is an agentic context engineering benchmark suite for measuring long-context agent behavior and retrieval-aware execution quality.
Stars54
Forks3
Updated2026-05-30
LicenseApache-2.0
Python benchmarkevaluationcontext-engineeringmemoryagent
Production Agent Runtime and Context Engineering Framework
Google AX
google/ax is a production-focused agent runtime framework that packages context engineering, orchestration, and evaluation-friendly primitives for real systems.
Stars1,300
Forks70
Updated2026-05-30
LicenseApache-2.0
Go agent-runtimeframeworkcontext-engineeringproductiongoogle
Automated Agent Harness Engineering Framework
AutoHarness
AutoHarness provides a governance-oriented runtime that wraps LLM clients and upgrades demo agents into auditable, policy-controlled production loops.
Stars295
Forks23
Updated2026-05-30
LicenseMIT
Python harnessgovernancemulti-agentself-improvementruntime
Agent Memory Poisoning Defense and Guard Layer
OWASP Agent Memory Guard
OWASP/www-project-agent-memory-guard
OWASP Agent Memory Guard is a runtime protection layer for agent memory operations, targeting memory poisoning, leakage, and integrity tampering.
Stars17
Forks10
Updated2026-05-30
LicenseApache-2.0
Python memorysecurityowaspprompt-injectionagentic-ai
Production Engineering Skill Pack for Coding Agents
Addy Agent Skills
addyosmani/agent-skills is a large-scale production skill pack that standardizes coding-agent engineering workflows and quality gates.
Stars47,000
Forks5200
Updated2026-05-30
LicenseMIT
Shell skillsworkflowcoding-agentquality-gatesplaybook
Open Agent Skills Registry and Distribution Layer
Zo Skills Registry
zocomputer/skills is an agent skills registry that unifies official, external, and community skill packages with validation and manifest generation.
Stars40
Forks40
Updated2026-05-30
LicenseMIT
TypeScript skillsregistrymanifestagent-runtimedistribution
State-Aware Financial Agent Benchmark Suite
QF-Bench
QF-Bench/QuantitativeFinance-Bench
QF-Bench is a state-aware benchmark dataset for evaluating AI agents on realistic quantitative finance workflows under sandboxed verification.
Stars28
Forks35
Updated2026-05-30
LicenseCC-BY-NC-4.0
Python benchmarkevaluationharboragentfinance
Self-Reflective Multi-Agent Defense System
AegisLLM
AegisLLM is a cooperative multi-agent security framework that claims self-improving defensive behavior through test-time prompt optimization.
Stars34
Forks4
Updated2026-05-30
LicenseMIT
Python multi-agentsecurityself-improvementdspyevaluation
Self-Evolving Memory and Reasoning Map Framework
EvoMap Evolver
EvoMap/evolver presents a memory-map framework that keeps updating graph structures from user and task feedback to improve retrieval and reasoning quality over time.
Stars7,600
Forks773
Updated2026-05-31
LicenseGPL-3.0
JavaScript memorygraphself-evolvingretrievalreasoning
On-Policy RL Self-Evolution Pipeline for Agent Models
Hermes Agent Self-Evolution
NousResearch/hermes-agent-self-evolution
NousResearch/hermes-agent-self-evolution packages a self-evolving RL training workflow that distills improved interaction behavior into Hermes model variants.
Stars3,700
Forks422
Updated2026-05-31
LicenseMIT
Python self-evolutionrlagent-trainingdistillationhermes
Graph-Memory MCP Server for Long-Horizon Agents
MCP Neo4j Agent Memory
knowall-ai/mcp-neo4j-agent-memory
knowall-ai/mcp-neo4j-agent-memory provides an MCP server that gives agents persistent graph memory backed by Neo4j plus vector retrieval.
Stars68
Forks15
Updated2026-05-31
LicenseMIT
TypeScript memoryneo4jmcpgraphlong-context
Codex/Claude Harness Skill Playbooks
CC Harness Skills
LearnPrompt/cc-harness-skills curates reusable harness playbooks for Codex and Claude Code workflows, emphasizing skill reuse over one-off prompts.
Stars217
Forks63
Updated2026-05-31
LicenseMIT
Markdown skillsharnesscodexclaude-codeplaybook
Interactive Computer-Use Benchmark Harness Arena
ClawArena
aiming-lab/ClawArena focuses on benchmark-centric evaluation for computer-use agents under controlled interactive environments.
Stars47
Forks0
Updated2026-05-31
LicenseMIT
Python benchmarkcomputer-useharnessevaluationagent
Curated Agent Skill Catalog and Prompt Workflow Patterns
Kodu Awesome Agent Skills
kodustech/awesome-agent-skills
kodustech/awesome-agent-skills is a curated index of reusable AI coding-agent skills and prompt workflow patterns.
Stars71
Forks29
Updated2026-05-31
LicenseCC0-1.0
Markdown skillsawesome-listprompt-patternscatalogagent-workflow
Persistent Context and Memory Orchestration for OpenClaw
Lossless Claw Context Management
Martian-Engineering/lossless-claw
Martian-Engineering/lossless-claw provides persistent context-management primitives for OpenClaw-style agent workflows with explicit long-horizon memory handling.
Stars4,800
Forks410
Updated2026-05-31
LicenseMIT
TypeScript memorycontextopenclawpluginlineage
Agentic RL and Benchmark Knowledge Index
AgentsMeetRL Benchmark Index
thinkwee/AgentsMeetRL is an awesome-style collection focused on agentic RL papers, methods, and benchmark references for agent training/evaluation loops.
Stars1,500
Forks203
Updated2026-05-31
LicenseNot listed
Markdown benchmarkagentic-rlevaluationawesome-listsurvey
Open Agent Harness Runtime and Evaluation Workflow
OpenHarness Agent Harness Fork
syntax-syndicate/OpenHarness-agent-harness
syntax-syndicate/OpenHarness-agent-harness tracks an OpenHarness runtime fork for controlled agent execution and evaluation workflow standardization.
Stars1
Forks0
Updated2026-05-31
LicenseMIT
Python harnessframeworkruntimeevaluationworkflow
OpenClaw Skill Plugin for Arcade Tool Connectivity
OpenClaw Arcade Plugin
ArcadeAI/openclaw-arcade-plugin
ArcadeAI/openclaw-arcade-plugin connects OpenClaw agents to Arcade.dev tool APIs as reusable plugin skills.
Stars4
Forks2
Updated2026-05-31
LicenseMIT
TypeScript openclawpluginskillstoolsintegration
OpenClaw Knowledge and Notes Integration Plugin
ObsidianClaw Knowledge Plugin
humanitylabs-org/obsidianclaw is an archived OpenClaw plugin that links agent workflows with Obsidian-style knowledge memory.
Stars6
Forks0
Updated2026-05-31
LicenseMIT
TypeScript memoryobsidianopenclawknowledge-baseplugin
Personal Assistant Plugin for OpenClaw Workflows
Momo OpenClaw Plugin
momo-personal-assistant/openclaw-plugin
momo-personal-assistant/openclaw-plugin provides an OpenClaw plugin layer for personal-assistant style workflows with persistent task context.
Stars15
Forks10
Updated2026-05-31
LicenseMIT
TypeScript assistantopenclawpluginmemoryapplication
Enterprise Agent Skill Registry and Runtime Templates
NVIDIA Agent Skills Registry
NVIDIA/skills curates reusable agent skill modules and templates for enterprise-grade assistant and coding workflows.
Stars692
Forks91
Updated2026-05-31
LicenseApache-2.0
Jupyter Notebook skillregistryagent-runtimeworkflownvidia
Agent Skill Packs and Prompt Compression Patterns
Supabase Agent Skills
supabase/agent-skills publishes composable skill packs for coding and product-support agent workflows with reusable prompt structures.
Stars2,200
Forks146
Updated2026-05-31
LicenseMIT
Markdown skillprompt-engineeringagentsupabaseworkflow
Self-Evolving Skill Selection and Benchmark Pipeline
Skills Vote Evolution Benchmark
MemTensor/skills-vote focuses on self-evolving skill selection and evaluation loops for agent improvement experiments.
Stars267
Forks14
Updated2026-05-31
LicenseMIT
Python benchmarkevaluationskill-evolutionself-improvingpython
Agent Memory Substrate and Runtime Tracing Harness
Ori Mnemos Memory Harness
aayoawoyemi/ori-mnemos provides a memory substrate that records agent traces and feeds retrieval into future steps.
Stars10
Forks0
Updated2026-05-31
LicenseMIT
TypeScript memoryruntimeagent-harnesstypescripttracing
Agent Channel Plugin for Enterprise Messaging Runtime
OpenClaw DingTalk Channel Plugin
soimy/openclaw-channel-dingtalk
soimy/openclaw-channel-dingtalk integrates OpenClaw agents with DingTalk channels for enterprise communication workflows.
Stars87
Forks38
Updated2026-05-31
LicenseMIT
TypeScript openclawpluginchanneldingtalkintegration
Harness-Oriented App Server for OpenClaw and Codex Workflows
OpenClaw Codex App Server
pwrdrvr/openclaw-codex-app-server
pwrdrvr/openclaw-codex-app-server exposes an app-server runtime linking OpenClaw workflows with Codex and provider integrations.
Stars258
Forks35
Updated2026-05-31
LicenseMIT
TypeScript openclawcodexapp-serverharnesstypescript
Agent Runtime Observability and Trace Monitoring Plugin
OpenClaw Observability Plugin
henrikrexed/openclaw-observability-plugin
henrikrexed/openclaw-observability-plugin adds observability and trace-monitoring capabilities to OpenClaw agent runtimes.
Stars0
Forks0
Updated2026-05-31
LicenseMIT
TypeScript openclawobservabilitytracingruntimeplugin
Self-Evolving OpenClaw Workflow Playground and Benchmark Harness
Self Evolve OpenClaw Playground
longmans/self-evolve is a self-learning OpenClaw plugin that learns from feedback and turns runtime experience into reusable memory.
Stars96
Forks5
Updated2026-06-08
LicenseMIT
TypeScript openclawself-evolvepluginepisodic memoryfeedback learning
OpenClaw Tracing Plugin for Langfuse Observability
OpenClaw Langfuse Observability Plugin
MCKRUZ/openclaw-langfuse adds Langfuse observability to OpenClaw through a lightweight plugin bridge.
Stars1
Forks0
Updated2026-06-01
LicenseMIT
JavaScript openclawlangfuseobservabilitytracingplugin
OpenClaw Memory and Context Enhancement Runtime
HyperSpell OpenClaw Memory Engine
hyperspell/hyperspell-openclaw
hyperspell/hyperspell-openclaw extends OpenClaw with memory/context synchronization and retrieval enhancements.
Stars181
Forks35
Updated2026-06-01
LicenseMIT
TypeScript memorycontextopenclawplugintypescript
OpenClaw Plugin Ecosystem Index and Skill Resource Map
Awesome OpenClaw Plugins (Composio Community)
composio-community/awesome-openclaw-plugins
composio-community/awesome-openclaw-plugins curates OpenClaw plugin assets and operational playbooks into a structured ecosystem index.
Stars43
Forks10
Updated2026-06-01
LicenseCC0-1.0
TypeScript openclawpluginsawesome-listskillsresource-index
Reproducible Agent Skill Benchmark and Evaluation Harness
Last30Days Skill Benchmark Harness
mvanhorn/last30days-skill provides a mature Python benchmark harness for evaluating agent skill performance over time.
Stars1,300
Forks147
Updated2026-06-01
LicenseMIT
Python benchmarkevaluationskillsharnesspython
OpenClaw Automation App and Productivity Workflow Plugin
ClawDreamer Automation Plugin
EESIZ/clawdreamer offers an OpenClaw-oriented automation app/plugin for productivity and workflow execution.
Stars23
Forks5
Updated2026-06-01
LicenseMIT
Python openclawautomationpluginapplicationpython
OpenClaw Plugin Catalog and Community Knowledge Index
Awesome OpenClaw Plugins (ThisIsJeron)
ThisIsJeron/awesome-openclaw-plugins
ThisIsJeron/awesome-openclaw-plugins is a curated OpenClaw plugin knowledge index with operational categories and install references.
Stars13
Forks12
Updated2026-06-01
LicenseCC0-1.0
Markdown openclawpluginsresource-indexcommunityskills
Agent Monetization Workflow and OpenClaw Use-Case Index
Awesome OpenClaw Money Maker Index
BlockRunAI/awesome-OpenClaw-Money-Maker
BlockRunAI/awesome-OpenClaw-Money-Maker curates OpenClaw-centric automation and skill pathways oriented toward real-world monetization scenarios.
Stars261
Forks45
Updated2026-06-01
LicenseCC0-1.0
Markdown openclawuse-casesautomationresource-indexmonetization
OpenClaw Ecosystem Curation and Skill Resource Index
Awesome OpenClaw Ecosystem Index (SamurAIGPT)
SamurAIGPT/awesome-openclaw is a curated index of OpenClaw resources, tools, skills, tutorials, and community projects.
Stars410
Forks72
Updated2026-06-01
LicenseLicense file present (public page)
Shell/JavaScript/HTML openclawskillsresource-indextutorialecosystem
OpenClaw Ecosystem Collection and Skill/Tool Index
Awesome Claws Collection (LHL3341)
LHL3341/awesome-claws curates OpenClaw products, skills, communities, and ecosystem resources in bilingual scenario-focused structure.
Stars129
Forks12
Updated2026-06-01
LicenseCC0-1.0
TypeScript openclawskillsresource-indexecosystemtutorial
Self-Improving Agent Policy Framework and Training Harness
REINS Self-Improving Model Framework
pegasi-ai/reins provides a self-improving control framework aimed at reducing undesired agent behavior during iterative execution.
Stars84
Forks7
Updated2026-06-01
LicenseMIT
Python evolutionframeworkreinforcementpolicyharness
Durable Agent Memory Graph Database and Skill Registry Runtime
MentisDB Agent Memory Graph Database
cloudllm-ai/mentisdb is a durable semantic memory engine and versioned skill registry for long-horizon AI agent operation.
Stars71
Forks8
Updated2026-06-01
LicenseMIT
Rust memorygraph-databaseskillsregistryrust
OpenClaw Plugin and Agent Skills Resource Index
Awesome OpenClaw Plugin Index (rohitg00)
rohitg00/awesome-openclaw is a high-activity curated index for OpenClaw plugins, skills, deployment patterns, and ecosystem resources.
Stars512
Forks123
Updated2026-06-01
LicenseCC0-1.0
Python openclawpluginsskillsresource-indexoperations
On-Device Memory Layer and Retrieval Runtime for Agents
ClawMem On-Device Memory Layer
yoloshii/ClawMem provides an on-device memory layer for Claude Code, Hermes, and OpenClaw agents with hybrid retrieval and hooks.
Stars179
Forks26
Updated2026-06-01
LicenseMIT
TypeScript memoryopenclawclaude-codemcprag
OpenClaw Fork with Multi-Tier Memory and Persona Runtime
SoulClaw OpenClaw Fork with Soul Memory
clawsouls/soulclaw is an OpenClaw-derived framework emphasizing persistent identity, multi-tier memory, and channel-ready agent runtime.
Stars7
Forks0
Updated2026-06-01
LicenseMIT
TypeScript openclawmemorypersonaframeworkmulti-agent
Multi-Agent Swarm Orchestration Runtime and Workflow Infrastructure
Commonly Agent Swarm Operating System
Team-Commonly/commonly positions itself as an AI swarm workflow operating system with built-in orchestration and repository-first execution patterns.
Stars685
Forks97
Updated2026-06-01
LicenseLicense file present (public page)
TypeScript swarmmulti-agentworkflowruntimeorchestration
OpenClaw Runtime Extension with Memory Control and Automation Rules
MateClaw OpenClaw Memory and Rule Engine
matevip/mateclaw extends the OpenClaw ecosystem with memory-aware runtime controls, rule-engine automation, and agent execution governance.
Stars537
Forks184
Updated2026-06-01
LicenseApache-2.0
Java openclawmemoryrule-engineautomationruntime
Security/Privacy Agent Plugin with Tooling and Channel Hardening
OnionClaw OPSEC Agent Plugin
christinminor459/OnionClaw is an OPSEC-focused OpenClaw plugin layer for secure agent execution and operational hardening.
Stars198
Forks56
Updated2026-06-01
LicenseLicense file present (public page)
Python openclawsecurityprivacyplugintooling
OpenClaw Community Skills and Runtime Integration Hub
Nowledge Community OpenClaw Skills Hub
nowledge-co/community acts as a community hub for OpenClaw skills, runtime integrations, and ecosystem collaboration resources.
Stars86
Forks21
Updated2026-06-01
LicenseLicense file present (public page)
TypeScript openclawcommunityskillsresource-indexruntime
Agent Context Protocol and Interoperability Tooling
LACP Lightweight Agent Context Protocol
0xNyk/lacp provides a lightweight agent context protocol aimed at reusable context passing and tool interoperability.
Stars261
Forks33
Updated2026-06-01
LicenseLicense file present (public page)
TypeScript protocolcontextmemoryinteroperabilityagent
Self-Improving Coding Agent with Benchmark-Oriented Execution
WATER Self-Improving Coding Agent
manthanguptaa/water targets self-improving coding agents with benchmark-linked execution loops and iterative optimization behavior.
Stars288
Forks38
Updated2026-06-01
LicenseApache-2.0
Python self-improvementcoding-agentbenchmarkevaluationevolution
Workflow Automation and Multi-Agent Control Infrastructure
Sponsio Workflow and Multi-Agent Control Plane
SponsioLabs/Sponsio provides workflow-centric multi-agent control infrastructure for orchestrated autonomous task execution.
Stars469
Forks28
Updated2026-06-01
LicenseLicense file present (public page)
TypeScript workflowmulti-agentcontrol-planeharnessautomation
Agent Workflow Memory Runtime with Knowledge Graph Integration
Agent Workflow Memory Knowledge Graph Runtime
zorazrw/agent-workflow-memory builds an agent workflow memory system with a graph-backed memory manager and FastAPI execution surface.
Stars440
Forks50
Updated2026-06-02
LicenseApache-2.0
Python memoryworkflowknowledge-graphruntimeagent
Benchmark Framework for Agent Memory Evaluation and Hallucination Testing
AgentMemory Benchmark Framework
webzler/agentMemory provides a benchmark framework focused on agent memory capability and hallucination-aware evaluation workflows.
Stars28
Forks4
Updated2026-06-02
LicenseMIT
TypeScript benchmarkmemoryevaluationhallucinationharness
Agentic Memory Architecture for LLM Agent Long-Term Context Retention
A-MEM Agentic Memory for LLM Agents
agiresearch/A-mem presents agentic memory infrastructure for LLM agents and targets long-term context quality in autonomous task loops.
Stars1,000
Forks86
Updated2026-06-02
LicenseMIT
Python memoryllm-agentagentic-memorylong-termframework
Agent Memory Plugin for ElizaOS Runtime and Persistent Context Handling
ElizaOS AgentMemory Plugin
elizaOS/agentmemory is a plugin module that enables memory management capabilities inside ElizaOS-based agent runtimes.
Stars236
Forks57
Updated2026-06-02
LicenseMIT
Python memorypluginelizaosruntimetooling
Reusable Skills Library for Coding Agents and Automation Workflows
Apify Agent Skills Library
apify/agent-skills curates reusable skills for coding agents to improve execution quality across software and automation tasks.
Stars2,100
Forks228
Updated2026-06-02
LicenseApache-2.0
Python skillscoding-agentworkflowlibraryautomation
Multi-Agent Swarm Orchestration Framework with Lightweight Runtime Control
OpenSwarm Multi-Agent Orchestration Framework
openswarm-ai/openswarm provides lightweight multi-agent orchestration primitives for building swarm-style autonomous workflows.
Stars129
Forks16
Updated2026-06-02
LicenseMIT
Python swarmmulti-agentorchestrationruntimeharness
Agentic Memory Runtime Framework for Persistent Context
AgentraLabs Agentic Memory Runtime
agentralabs/agentic-memory provides an agent memory runtime package focused on persistent context and reusable memory APIs.
Stars18
Forks4
Updated2026-06-02
LicenseMIT
TypeScript memoryagentic-memoryruntimecontextagent
Pluggable Agentic Memory Module for Any Agent System
LHL Agentic Memory Module
lhl/agentic-memory is a simple memory implementation designed to be slotted into any agentic system.
Stars246
Forks25
Updated2026-06-02
LicenseUnspecified
TypeScript memorymoduleagentic-systemplugincontext
Agent Evaluation Harness with LangGraph Integrations
LangChain AgentEvals Harness
langchain-ai/agentevals is a LangChain ecosystem harness for running repeatable agent evaluation suites.
Stars76
Forks9
Updated2026-06-02
LicenseMIT
Python evaluationbenchmarklanggraphharnessagent
Benchmark and Evaluation Framework for Agent Systems
AgentEvals.dev Benchmark Framework
agentevals-dev/agentevals provides an Apache-licensed benchmark framework for evaluating agent behavior and quality changes.
Stars98
Forks6
Updated2026-06-02
LicenseApache-2.0
Python benchmarkevaluationagentqualityframework
Memory Methods Library for Cognitive Agent Architectures
ALucek Agentic Memory Methods Library
ALucek/agentic-memory curates practical memory implementation methods for agentic LLM systems inspired by cognitive architecture concepts.
Stars462
Forks91
Updated2026-06-02
LicenseUnspecified
Python memorymethodscognitive-architecturetutorialagent
General Agentic Memory Framework with Cross-Task Reuse
VectorSpaceLab General Agentic Memory
VectorSpaceLab/general-agentic-memory
VectorSpaceLab/general-agentic-memory focuses on generalized memory abstractions that can be reused across varied agent workloads.
Stars390
Forks32
Updated2026-06-02
LicenseUnspecified
Python memoryframeworkgeneralizationruntimeagent
Context-Aware Long-Term Memory Engine for AI Agents
Nocturne Memory Context Engine
Dataojitori/nocturne_memory is a context-aware long-term memory engine for AI agents with sustained repository activity.
Stars1,200
Forks147
Updated2026-06-02
LicenseMIT
Python memorycontext-awarelong-termengineagent
CLI Agent Evaluation Harness with Schema-Driven Trial Pipelines
Plaited Agent Eval Harness
plaited/agent-eval-harness provides a Unix-style, schema-driven evaluation harness for CLI agents with run, grade, compare, and calibrate modes.
Stars3
Forks1
Updated2026-06-02
LicenseISC
TypeScript evaluationharnesscli-agentschemabenchmark
Enterprise Multi-Agent Evaluation and Verification Harness
MultiAgentEval Enterprise Harness
najeed/ai-agent-eval-harness is an enterprise-grade reliability framework for AI agents with benchmark, replay, and verification surfaces.
Stars28
Forks6
Updated2026-06-02
LicenseApache-2.0
Python evaluationverificationenterprisemulti-agentharness
Stateful Continual-Learning Benchmark for LLM Agents
Arc Continual Learning Benchmark
Arc-Computer/CL-Bench is a benchmark framework for evaluating LLM agent continual learning in stateful environments with CRM-style workflows.
Stars19
Forks3
Updated2026-06-02
LicenseApache-2.0
Python continual learning benchmarkcrm workflowstateful evaltool validationagent benchmark
Persistent Memory Runtime for OpenClaw-Style AI Agents
ClawVault Memory Runtime
Versatly/clawvault provides structured persistent memory for AI agents and exposes benchmarks, docs, and eval surfaces around that memory stack.
Stars646
Forks62
Updated2026-06-02
LicenseMIT
TypeScript memoryruntimeopenclawpersistent-contextagent
Token-Efficient Agent Runtime with OpenClaw/MCP/Memory Integration
OpenSquilla Token-Efficient Agent Runtime
opensquilla/opensquilla is a token-efficient AI agent runtime focused on higher intelligence density with OpenClaw, memory, and MCP integration signals.
Stars2,184
Forks148
Updated2026-06-01
LicenseApache-2.0
Python runtimeopenclawmemorymcptoken-efficiency
Desktop Agent Runtime and Multi-Mode Execution Environment
BitFun Desktop Agent Runtime Suite
GCWing/BitFun provides a desktop-grade agent runtime suite with built-in code/cowork/computer-use flows plus persistent memory and evolving behavior claims.
Stars799
Forks99
Updated2026-06-01
LicenseMIT
Rust desktopruntimecomputer-usememorymulti-mode
Agent Memory Plugin and Retrieval Augmentation Layer
PowerMem Agent Memory Plugin
oceanbase/powermem is an agent memory plugin focused on improving accuracy, agility, and affordability for AI agent memory retrieval.
Stars688
Forks83
Updated2026-06-01
LicenseNOASSERTION
Python memorypluginretrievalagentruntime
Persistent Memory Substrate for Cross-Session Agent Recall
Mnemon Persistent Memory Substrate
mnemon-dev/mnemon provides LLM-supervised persistent graph memory for agents across Claude Code, OpenClaw, and other CLI runtimes.
Stars322
Forks46
Updated2026-06-01
LicenseApache-2.0
Go memorygraphcross-sessionopenclawcli-agent
Semantic/Episodic/Procedural Memory Runtime for Agents
Mengram Human-Like Agent Memory
alibaizhanov/mengram offers human-like semantic/episodic/procedural memory infrastructure for AI agents with multi-framework integrations.
Stars172
Forks27
Updated2026-06-01
LicenseApache-2.0
Python memorysemanticepisodicproceduralsdk
Shared Agent Context, Memory, and Supervised Execution Layer
IMCodes Shared Agent Context Layer
im4codes/imcodes focuses on shared agent context and memory with supervised execution and cross-agent audit capabilities.
Stars131
Forks11
Updated2026-06-01
LicenseMIT
TypeScript contextmemoryauditcross-agenttooling
Agent Benchmark Toolkit for Query/Retrieval Evaluation
Weaviate Query Agent Benchmarking Toolkit
weaviate/query-agent-benchmarking
weaviate/query-agent-benchmarking provides benchmarking scenarios and tooling for evaluating Weaviate query-agent behavior.
Stars15
Forks3
Updated2026-06-01
LicenseBSD-3-Clause
Jupyter Notebook benchmarkevaluationquery-agentretrievaltoolkit
Real-world agent task benchmark
PinchBench Skill
PinchBench is an OpenClaw-oriented real task benchmark that measures coding agents across productivity, research, writing, coding, analysis, email, memory, and skill-discovery tasks.
Stars1,261
Forks144
Updated2026-07-02
LicenseMIT
Python benchmarkevaluationopenclawskillstranscripts
Agent Memory Benchmark
Agent Memory Benchmark
vectorize-io/agent-memory-benchmark
vectorize-io/agent-memory-benchmark is a benchmark harness for comparing agent memory strategies on multi-step tasks where retrieval quality, latency, and token cost all matter.
Stars46
Forks17
Updated2026-06-04
LicenseUnknown
Python memorybenchmarkevaluationcostretrievalbenchmark-eval
External awesome list and taxonomy comparator
EvoMap Awesome Agent Evolution
EvoMap/awesome-agent-evolution
EvoMap/awesome-agent-evolution is a curated awesome list covering self-evolution, memory, protocols, benchmarks, coding agents, and adjacent infrastructure.
Stars163
Forks23
Updated2026-07-01
LicenseNOASSERTION
JavaScript taxonomyawesome-listmemorybenchmarkagent-swarm
Autonomous Java Bug Repair Agent
RepairAgent
RepairAgent is an autonomous agent that fixes bugs in Java projects using LLMs through a localize-analyze-fix-test iteration loop.
Stars99
Forks32
Updated2026-06-03
LicenseMIT
Python code repairdefects4jbug fixing agentjavaautonomous debugging
Self-Improving Accelerator Kernel Optimization Agent
AccelOpt
AccelOpt is a self-improving LLM agentic system that iteratively optimizes AI accelerator kernels using optimization memory and benchmarked kernel profiling.
Stars51
Forks7
Updated2026-06-03
LicenseApache-2.0
Python self-improving agentkernel optimizationnkibenchflashinfer-benchaccelerator tuning
Auditable Local-First Code Agent Baseline
DM-Code-Agent
DM-Code-Agent is a local-first and auditable Python code agent baseline with explicit planning, trace replay, optional reflexion modules, and benchmark-facing evaluation paths.
Stars138
Forks12
Updated2026-06-03
LicenseMIT
Python code agenttrace replayswe-bench litelocal firstauditable
Last-Token Self-Rewarding Reinforcement Learning Recipe
LaSeR
LaSeR is a reinforcement-learning recipe that jointly improves reasoning and self-rewarding behavior by adding an MSE self-reward term to the RLVR objective.
Stars36
Forks2
Updated2026-06-03
LicenseMIT
Python self rewardrlvrreasoning optimizationpaper codecheckpoint release
Knowledge-Graph Agentic RAG Runtime
GraphMind
GraphMind is an agentic RAG runtime that combines knowledge graphs, dual orchestration engines, and self-evaluating retrieval pipelines for autonomous knowledge work.
Stars1
Forks0
Updated2026-06-03
LicenseMIT
Python knowledge graphagentic raglanggraphcrewaiself evaluation
Agent Memory Resource Survey Index
Awesome Agent Memory
agentmemoryworld/awesome-agent-memory
Awesome Agent Memory is an up-to-date survey index for agent-memory papers, systems, and benchmarks rather than a runnable memory runtime.
Stars155
Forks8
Updated2026-06-04
LicenseUnknown
Markdown memorysurvey indexresource mapbenchmark entrypointagent memory
Continual Learning And Long-Term Memory SDK
Learning SDK
Learning SDK is a drop-in memory and continual-learning substrate for existing LLM agents, exposing a thin wrapper instead of a full custom runtime.
Stars45
Forks3
Updated2026-06-04
LicenseApache-2.0
Python memory runtimecontinual learningstateful agentssdkprovider-agnostic
Code-As-Agent-Harness Survey Index
Awesome Code as Agent Harness Papers
yennning/awesome-code-as-agent-harness-papers
Awesome Code as Agent Harness Papers is a harness-first survey index that turns code-centric agent systems into an organized reading and comparison map.
Stars331
Forks24
Updated2026-06-04
LicenseMIT
Markdown harnesssurvey indexcode agentstaxonomymulti-agent topology
Safe Self-Evolving Agent Framework
Geneclaw
Geneclaw is a safe-by-default self-evolving agent framework that observes failures, proposes fixes, and only applies changes behind an explicit safety gate.
Stars36
Forks8
Updated2026-06-04
LicenseMIT
Python self-evolving agentssafety gatekeeperagent evolutionrollbackbenchmark hooks
Trace-Scored Full-Stack Agent Benchmark
ClawBench
ClawBench is a benchmark for agent systems that scores the full stack through execution traces, reliability metrics, and diagnostics rather than only final-task success.
Stars106
Forks19
Updated2026-06-04
LicenseMIT
Python benchmarktrace scoringharness evaluationreliabilitydiagnostics
Agent Skills Resource Index
Awesome Agent Skills
voltagent/awesome-agent-skills
voltagent/awesome-agent-skills is a high-signal resource index for reusable agent skills across Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and adjacent coding-agent surfaces.
Stars24,200
Forks2600
Updated2026-06-04
LicenseMIT
Markdown skillresource-index
Self-Hosted Agent Runtime
swarmclaw
swarmclawai/swarmclaw is a self-hosted multi-agent runtime that combines memory, MCP tooling, delegation, schedules, skills, and swarm-oriented execution surfaces.
Stars544
Forks106
Updated2026-06-04
LicenseMIT
TypeScript harnessframework-runtime
Production Multi-Agent Orchestration Runtime
Swarms
Swarms is a production-oriented multi-agent orchestration framework that packages sequential, concurrent, and hierarchical agent topologies with tools, memory, protocol adapters, and marketplace-style extensions.
Stars6,800
Forks935
Updated2026-05-28
LicenseApache-2.0
Python multi-agentswarmorchestrationmcpproduction-runtime
Production Coding-Agent Swarm Orchestrator
Agent Orchestrator
AgentWrapper/agent-orchestrator
Agent Orchestrator is a production coding-agent swarm that runs spec, build, test, review, and merge flows through Git worktrees, skills, memory, and MCP-connected execution.
Stars7,514
Forks1025
Updated2026-06-09
LicenseMIT
TypeScript coding-agentswarmharnessworktreemcp
Personalized Healthcare Agent Memory Benchmark
MedMemoryBench
MedMemoryBench is a benchmark for agent memory in personalized healthcare, testing whether clinical agents retain, retrieve, and use longitudinal patient context safely and accurately.
Stars60
Forks1
Updated2026-05-13
LicenseApache-2.0
Python memorybenchmarkhealthcarelongitudinal-context
Compounding Lead-Worker Agent Runtime
Agent Swarm
Agent Swarm is a compounding lead-worker runtime that packages delegation topology, worker isolation, shared memory, MCP tooling, and recurring workflows into one public swarm system.
Stars573
Forks65
Updated2026-07-04
LicenseMIT
TypeScript agent-swarmlead-workerdockermcpcompounding-memory
OpenAI Agents SDK Swarm Orchestrator
Agency Swarm
Agency Swarm is a mature Python orchestration framework that layers role-aware communication flows, type-safe tools, thread persistence, and terminal/web demos on top of the OpenAI Agents SDK.
Stars4,445
Forks1058
Updated2026-06-12
LicenseMIT
Python agency-swarmopenai-agents-sdkmulti-agentstate-persistencecli
Continual Experience and Skill Learning Paper Code
XSkill
XSkill is a multimodal continual-learning paper implementation that extracts task-level skills and action-level experiences from agent trajectories, stores them in a memory bank, and re-injects them during inference across benchmark suites.
Stars221
Forks27
Updated2026-05-13
LicenseNOASSERTION
Python xskillcontinual-learningmemory-bankskillsbenchmark
Memory/MCP Skill Agent Framework
LightAgent
LightAgent is a lightweight Python agent framework that combines persistent memory, MCP integration, native skills, LightSwarm collaboration, and newly surfaced LightFlow workflow orchestration into a small-footprint self-learning runtime.
Stars1,132
Forks143
Updated2026-06-05
LicenseApache-2.0
Python lightagentmemorymcpskillsworkflow
Official OpenAI Agents SDK Runtime Baseline
OpenAI Agents SDK (Python)
OpenAI Agents SDK (Python) is the official Python baseline for multi-agent orchestration with handoffs, tool calls, guardrails, tracing, and session state.
Stars27,111
Forks4185
Updated2026-06-11
LicenseMIT
Python openai-agents-sdkofficial-sdkpythonorchestrationguardrails
Official OpenAI Agents SDK TypeScript Baseline
OpenAI Agents SDK (JS)
OpenAI Agents SDK (JS) is the official TypeScript baseline for building agent orchestration loops with tools, handoffs, guardrails, realtime hooks, and tracing.
Stars3,203
Forks809
Updated2026-06-12
LicenseMIT
TypeScript openai-agents-sdkofficial-sdktypescriptorchestrationrealtime
Harness evolution engineering
Agentic Harness Engineering
china-qijizhifeng/agentic-Harness-engineering
Harness engineering is the layer where prompts, tools, middleware, memory, subagents, and evaluators become editable agent infrastructure rather than fixed wrappers around a base model.
Stars685
Forks75
Updated2026-06-14
LicenseMIT
Python harnessskillsmemoryevaluationcoding-agent
Self-improving personal agent runtime
Hermes Agent
Hermes Agent is a self-improving personal-agent runtime that combines memory, skill creation, session search, user modeling, messaging gateways, and scheduled automations in one user-facing system.
Stars209,194
Forks38173
Updated2026-07-04
LicenseMIT
Python personal-agentmemoryskillsmessagingautomation
Token-efficient self-evolving agent
GenericAgent
GenericAgent is a minimal self-evolving autonomous agent framework that grows a skill tree from a small seed loop instead of preloading a large fixed procedure library.
Stars13,284
Forks1535
Updated2026-07-02
LicenseMIT
Python self-evolvingskill-treememory-systemautonomous-agenttoken-efficiency
Personal agent product runtime
OpenClaw
OpenClaw is a local-first personal AI agent runtime with multi-channel interaction, durable sessions, skills, companion apps, and product-facing operating workflows.
Stars381,730
Forks80030
Updated2026-07-04
LicenseNOASSERTION
TypeScript personal-agentlocal-firstchannelsskillsruntime
Agentic skills methodology
Superpowers
Superpowers is a cross-agent skill and workflow methodology library that packages reusable operating habits for Claude Code, Codex, Cursor, and adjacent coding agents.
Stars246,190
Forks21830
Updated2026-07-02
LicenseMIT
Shell skillscoding-agentworkflowmethodologyworktrees
Agent persistent memory layer
agentmemory
agentmemory is a cross-harness persistent memory layer for coding agents and MCP clients, with wiki-style knowledge capture, retrieval, and continuity signals.
Stars24,554
Forks2021
Updated2026-06-29
LicenseApache-2.0
TypeScript memorymcpcoding-agentknowledge-graphcontinuity