Card Wall / 卡片墙

项目 × 研究 × 博客

一张卡片代表一个项目、一篇研究笔记或一篇博客文章。点击浏览详情。

300个项目
19篇研究
25篇博客
344张卡片
📦 项目 进化式代码优化

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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 自进化 Agent 综述

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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 LLM Agent 优化综述

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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 自进化 Agent 综述

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。

📦 项目 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。

📦 项目 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)。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 Agent 研究综述

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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 Agent 框架

smolagents

smolagents HuggingFace 轻量级 Agent 框架,简洁 API 构建 AI Agent。

📦 项目 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。

📦 项目 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。

📦 项目 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。

📦 项目 Agent 研究综述

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。

📦 项目 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.

📦 项目 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.

📦 项目 Graph-Based Agent Memory Index

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Memory Technique Cookbook

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Self-Improving Coding Agent

SICA 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.

📦 项目 Autonomous Agent Runtime

Agent Zero

Agent Zero is an autonomous-agent runtime with Linux execution, memory, browser automation, skills, plugins, projects and subordinate agents.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Research Skill Library

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.

📦 项目 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.

📦 项目 Domain Agent Skill Workflow Pack

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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。

📦 项目 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。

📦 项目 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.

📦 项目 Meta-harness framework and reference experiments

Meta-Harness (Stanford IRIS)

Meta-Harness provides reference code for automated search over model harnesses, including terminal benchmark scaffold evolution and text-classification memory-system search.

📦 项目 Hermes Benchmark Outer-Loop Harness

Hermes Benchmark Outer-Loop Harness

Hermes Agent Meta-Harness is a standalone outer-loop evaluator that optimizes Hermes benchmark harness candidates without modifying model weights.

📦 项目 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.

📦 项目 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.

📦 项目 OpenClaw Long-Term Memory Plugin

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Cross-Platform Agent Skill Index

Awesome Agent Skills

junminhong/awesome-agent-skills curates reusable skill workflows and templates for Codex, Claude Code, and other agent platforms.

📦 项目 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.

📦 项目 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.

📦 项目 Harness Curation and Reading Map

Awesome Agent Harness (AutoJunjie)

AutoJunjie/awesome-agent-harness curates the emerging agent harness ecosystem, combining benchmark references and implementation pointers.

📦 项目 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.

📦 项目 Multi-Domain Agent Benchmark Pack

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.

📦 项目 Long-Horizon Agent Environment

holaOS

holaOS is an agent environment focused on long-horizon continuity, context retention, and self-evolving workflows for autonomous execution.

📦 项目 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.

📦 项目 Deterministic AI Coding Harness Builder

Archon

Archon is an open-source harness builder for AI coding that turns development processes into deterministic, reusable workflows.

📦 项目 Ranked Agent Harness Landscape Index

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.

📦 项目 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.

📦 项目 Local Long-Term Agent Memory Substrate

TencentDB Agent Memory

TencentDB Agent Memory provides a local-first long-term memory pipeline for AI agents with plugin integration and benchmarked efficiency gains.

📦 项目 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.

📦 项目 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.

📦 项目 OpenClaw Skill and Agent Workflow Index

Awesome OpenClaw Skills

awesome-openclaw-skills is a large curated index of OpenClaw skills, prompts, and reusable agent workflow assets.

📦 项目 OpenClaw Community Landscape and Resources

Awesome OpenClaw

awesome-openclaw curates OpenClaw ecosystem resources including skills, runtime guidance, and adjacent project links.

📦 项目 Quantitative Agent Harness Runtime

QuantClaw

QuantClaw is an autonomous quantitative agent runtime built around OpenClaw-style agent workflows for market analysis and execution tasks.

📦 项目 Scientific Agent Skill and Tooling Index

Awesome Scientific Skills

Awesome-Scientific-Skills is a curated list of scientific-agent skills, tools, and workflows intended for reusable research automation.

📦 项目 Open-Ended Agent Benchmark Harness

ClawBench

ClawBench is an open-ended agent benchmark built for evaluating long-horizon OpenClaw-style agent performance and generalization.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Execution-Intent Memory Benchmark Harness

Continuity Benchmarks

continuity-benchmarks provides reproducible execution-intent memory benchmarks for long-horizon AI coding agents with LongMemEval-S and ID-RAG matrix evaluation.

📦 项目 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.

📦 项目 Procedural Memory Retrieval Benchmark

Procedural Memory Benchmark

Proced_mem_bench benchmarks procedural memory retrieval for language agents across ALFWorld trajectories and upcoming OSWorld scenarios.

📦 项目 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.

📦 项目 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.

📦 项目 Model Safety Benchmark and Reporting Framework

MLCommons ModelBench

MLCommons modelbench runs safety benchmarks against AI models and publishes detailed hazard-oriented benchmark reports.

📦 项目 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.

📦 项目 Agent Skill Security Resource Index

Awesome Agent Skills Security

awesome-agent-skills-security curates security and benchmark resources specifically for agent skill systems and tool-use workflows.

📦 项目 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.

📦 项目 Reusable Agent Skill Library

Agent Skills

agent-skills provides reusable operational skill bundles designed to be installed and maintained across agent runtimes.

📦 项目 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.

📦 项目 Provenance-Aware Memory Benchmark Framework

Tiermem

Tiermem introduces benchmark tasks that jointly evaluate memory answer quality and provenance consistency for long-term AI assistants.

📦 项目 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.

📦 项目 Runtime Agent Skill Loader

Agent Skill Loader

agent-skill-loader provides a TypeScript loader pipeline for wiring reusable skill modules into AI agent runtimes.

📦 项目 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.

📦 项目 Mobile Agent Self-Evolution Framework

Darwin Mobile Agent

darwin-mobile-agent targets self-evolving mobile automation agents with an explicit iterative improvement workflow.

📦 项目 Long-Term Memory Benchmark Suite

Mem-Gallery

Mem-Gallery provides a benchmark suite for long-term memory capability in LLM-based agents and assistants.

📦 项目 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.

📦 项目 Maintainer Codex Harness for Issue Clusters

Clownfish

clownfish is OpenClaw's maintainer codex harness focused on resolving issue clusters at scale with auditable workflows.

📦 项目 OpenClaw Plugin Compatibility Testbed

Crabpot

crabpot is a compatibility testbed repository for OpenClaw community plugins and plugin seam validation.

📦 项目 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.

📦 项目 Shared Crawl Infrastructure Toolkit

Crawlkit

crawlkit is OpenClaw's shared Go infrastructure for local-first crawler and archive processing workflows.

📦 项目 Discord Archive and Memory Ingest Harness

Discrawl

discrawl is a Discord CLI crawler with SQLite-backed archival pipelines for building reusable organizational memory datasets.

📦 项目 Hosted Agent Memory Runtime Plugin

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Browser Agent Benchmark and Evaluation Harness

Crabbox

crabbox is OpenClaw's browser-agent benchmark framework for reproducible task execution and evaluator-driven comparison.

📦 项目 Windows Companion Runtime for Agent Execution

OpenClaw Windows Node

openclaw-windows-node provides a Windows companion runtime layer to execute OpenClaw agent workflows in native Windows contexts.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Cross-Framework Agent Skills Registry

Awesome Agent Skills (Skillmatic)

skillmatic-awesome-agent-skills is a large cross-framework directory of reusable agent skills spanning Codex, Claude Code, Cursor, Gemini, and other runtimes.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Evaluation Harness and Regression Pipeline

EvalMonkey

EvalMonkey provides a lightweight evaluation harness for LLM agents with regression workflows and reusable benchmark checks.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Memory Poisoning Defense and Guard Layer

OWASP Agent Memory Guard

OWASP Agent Memory Guard is a runtime protection layer for agent memory operations, targeting memory poisoning, leakage, and integrity tampering.

📦 项目 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.

📦 项目 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.

📦 项目 State-Aware Financial Agent Benchmark Suite

QF-Bench

QF-Bench is a state-aware benchmark dataset for evaluating AI agents on realistic quantitative finance workflows under sandboxed verification.

📦 项目 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.

📦 项目 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.

📦 项目 On-Policy RL Self-Evolution Pipeline for Agent Models

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.

📦 项目 Graph-Memory MCP Server for Long-Horizon Agents

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.

📦 项目 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.

📦 项目 Interactive Computer-Use Benchmark Harness Arena

ClawArena

aiming-lab/ClawArena focuses on benchmark-centric evaluation for computer-use agents under controlled interactive environments.

📦 项目 Curated Agent Skill Catalog and Prompt Workflow Patterns

Kodu Awesome Agent Skills

kodustech/awesome-agent-skills is a curated index of reusable AI coding-agent skills and prompt workflow patterns.

📦 项目 Persistent Context and Memory Orchestration for OpenClaw

Lossless Claw Context Management

Martian-Engineering/lossless-claw provides persistent context-management primitives for OpenClaw-style agent workflows with explicit long-horizon memory handling.

📦 项目 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.

📦 项目 Open Agent Harness Runtime and Evaluation Workflow

OpenHarness Agent Harness Fork

syntax-syndicate/OpenHarness-agent-harness tracks an OpenHarness runtime fork for controlled agent execution and evaluation workflow standardization.

📦 项目 OpenClaw Skill Plugin for Arcade Tool Connectivity

OpenClaw Arcade Plugin

ArcadeAI/openclaw-arcade-plugin connects OpenClaw agents to Arcade.dev tool APIs as reusable plugin skills.

📦 项目 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.

📦 项目 Personal Assistant Plugin for OpenClaw Workflows

Momo OpenClaw Plugin

momo-personal-assistant/openclaw-plugin provides an OpenClaw plugin layer for personal-assistant style workflows with persistent task context.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Channel Plugin for Enterprise Messaging Runtime

OpenClaw DingTalk Channel Plugin

soimy/openclaw-channel-dingtalk integrates OpenClaw agents with DingTalk channels for enterprise communication workflows.

📦 项目 Harness-Oriented App Server for OpenClaw and Codex Workflows

OpenClaw Codex App Server

pwrdrvr/openclaw-codex-app-server exposes an app-server runtime linking OpenClaw workflows with Codex and provider integrations.

📦 项目 Agent Runtime Observability and Trace Monitoring Plugin

OpenClaw Observability Plugin

henrikrexed/openclaw-observability-plugin adds observability and trace-monitoring capabilities to OpenClaw agent runtimes.

📦 项目 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.

📦 项目 OpenClaw Tracing Plugin for Langfuse Observability

OpenClaw Langfuse Observability Plugin

MCKRUZ/openclaw-langfuse adds Langfuse observability to OpenClaw through a lightweight plugin bridge.

📦 项目 OpenClaw Memory and Context Enhancement Runtime

HyperSpell OpenClaw Memory Engine

hyperspell/hyperspell-openclaw extends OpenClaw with memory/context synchronization and retrieval enhancements.

📦 项目 OpenClaw Plugin Ecosystem Index and Skill Resource Map

Awesome OpenClaw Plugins (Composio Community)

composio-community/awesome-openclaw-plugins curates OpenClaw plugin assets and operational playbooks into a structured ecosystem index.

📦 项目 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.

📦 项目 OpenClaw Automation App and Productivity Workflow Plugin

ClawDreamer Automation Plugin

EESIZ/clawdreamer offers an OpenClaw-oriented automation app/plugin for productivity and workflow execution.

📦 项目 OpenClaw Plugin Catalog and Community Knowledge Index

Awesome OpenClaw Plugins (ThisIsJeron)

ThisIsJeron/awesome-openclaw-plugins is a curated OpenClaw plugin knowledge index with operational categories and install references.

📦 项目 Agent Monetization Workflow and OpenClaw Use-Case Index

Awesome OpenClaw Money Maker Index

BlockRunAI/awesome-OpenClaw-Money-Maker curates OpenClaw-centric automation and skill pathways oriented toward real-world monetization scenarios.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Evaluation Harness with LangGraph Integrations

LangChain AgentEvals Harness

langchain-ai/agentevals is a LangChain ecosystem harness for running repeatable agent evaluation suites.

📦 项目 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.

📦 项目 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.

📦 项目 General Agentic Memory Framework with Cross-Task Reuse

VectorSpaceLab General Agentic Memory

VectorSpaceLab/general-agentic-memory focuses on generalized memory abstractions that can be reused across varied agent workloads.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Benchmark Toolkit for Query/Retrieval Evaluation

Weaviate Query Agent Benchmarking Toolkit

weaviate/query-agent-benchmarking provides benchmarking scenarios and tooling for evaluating Weaviate query-agent behavior.

📦 项目 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.

📦 项目 Agent Memory Benchmark

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.

📦 项目 External awesome list and taxonomy comparator

EvoMap Awesome Agent Evolution

EvoMap/awesome-agent-evolution is a curated awesome list covering self-evolution, memory, protocols, benchmarks, coding agents, and adjacent infrastructure.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Memory Resource Survey Index

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.

📦 项目 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.

📦 项目 Code-As-Agent-Harness Survey Index

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.

📦 项目 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.

📦 项目 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.

📦 项目 Agent Skills Resource Index

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.

📦 项目 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.

📦 项目 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.

📦 项目 Production Coding-Agent Swarm Orchestrator

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 Harness evolution engineering

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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

📦 项目 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.

🔬 研究 LLM 自我改进

Self-Refine:基于自反馈的迭代式优化

同一 LLM 生成答案、批评答案并在推理期迭代改写,是轻量 Self Evolve 循环的基线模式。

🔬 研究 LLM 自我改进

Reflexion:带语言强化学习的智能体

把失败反馈转化为自然语言反思并写入记忆,让后续任务在不更新权重的情况下改进。

🔬 研究 LLM 自我改进

Teaching LLMs to Self-Debug

把执行结果、测试和调试解释作为程序修复信号,直接支撑代码智能体的回归门禁。

🔬 研究 LLM 自我改进

SPIN:Self-Play Fine-Tuning

通过自博弈微调把弱模型推向更强模型,把自我改进从提示期推进到训练期。

🔬 研究 进化计算 + LLM

OPRO:Large Language Models as Optimizers

用自然语言描述目标和历史分数,让 LLM 基于反馈提出新候选,是通用“LLM 即优化器”模板。

🔬 研究 进化计算 + LLM

FunSearch:LLM + 评估器的程序进化

把 LLM 与自动评估器组合,进化数学和科学发现程序,是“生成器 + 验证器 + 谱系”的重要案例。

🔬 研究 AutoML + LLM

AutoML-Agent:多 Agent 全流程 AutoML

将数据检索、预处理、建模、评估和部署拆成专用 Agent,最接近产品化 Self Evolve 工作流。

🔬 研究 NAS + LLM

EvoPrompting:代码级神经架构搜索

把语言模型作为架构代码的变异算子,用 Benchmark 选择候选,体现“架构即基因组”。

🔬 研究 Agent 框架进化

AutoGen / MetaGPT / CrewAI:Agent 编排底座

Agent 框架提供角色、工具和流程编排;Self Evolve 可在其上叠加评估器、记忆、谱系和回归防护。

🔬 研究 LLM 自我改进

Agent Symbolic Learning:符号反向传播驱动的自进化智能体

将智能体视为符号网络,用"语言梯度"在自然语言空间做反向传播,让提示词、工具和管线自动进化。NeurIPS 2024。

🔬 研究 Agent 自我进化

Darwin Gödel Machine:开放式自进化 Agent 归档

结合达尔文进化与哥德尔机自引用,维护开放式 Agent 归档库。SWE-bench 20%→50%,Polyglot 14.2%→30.7%。

🔬 研究 Agent 自我进化

Gödel Agent:运行时 monkey patching 自修改

通过 monkey patching 实现 Agent 在运行时的自修改,结合自我评估与进化策略动态调整自身代码。

🔬 研究 Agent 自我进化

ADAS:智能体系统自动设计

在图灵完备的 Python 代码空间中搜索最优 Agent 架构,发现的 Agent 跨领域、跨模型迁移且超越人工设计 SOTA。ICLR 2025。

🔬 研究 进化计算 + LLM

AlphaEvolve:Gemini 驱动的进化式算法发现

结合 Gemini Flash(广度)+ Pro(深度)做 MAP-Elites 质量多样性搜索;报告了 4×4 complex-valued matrix multiplication 的 48-scalar result。Google DeepMind。

🔬 研究 LLM 自我改进

Absolute Zero:零数据自博弈推理强化学习

单一模型同时提出任务并求解,仅用自生成数据进行自博弈 RL 训练,彻底消除对外部标注数据的依赖。NeurIPS 2025。

🔬 研究 LLM 自我改进

SelfEvolve:自生成知识 + 迭代自调试

LLM 自生成 API 文档作为知识来源,然后在沙盒中执行代码并将错误反馈回 LLM 进行迭代修复。

🔬 研究 LLM 自我改进

RISE:推理期自编辑强化学习

通过迭代式自编辑(self-edit)让 LLM 在推理时修改自身输出,结合 RL 训练让模型学会何时及如何修改。

🔬 研究 Agent 自我进化

RAGEN:轨迹级 Agent 强化学习

在轨迹级别对 Agent 进行强化学习训练,让 Agent 从完整交互历史中学习策略改进。

🔬 研究 LLM 自我改进

ReVeal:多轮代码 RL 持续改进

多轮代码生成与验证的 RL 框架,让模型在迭代修复循环中持续改进代码质量。Google DeepMind。

📝 博客 博客

Anthropic Dynamic Workflows:为什么它是 Agent-Swarm Evolve 的热点证据

把 Claude Code dynamic workflows 放回 Self Evolve 主题:它不是普通多 Agent,而是让任务组织、验证队列、并行子代理和安全边界一起变成可审计的 Agent-Swarm Evolve。

📝 博客 博客

Anthropic 五月热点:从 Opus 4.8、Stainless 到 965B 估值,AgentOps 栈正在成型

把 Anthropic 2026 年 5 月的 Opus 4.8、Dynamic Workflows、Stainless 收购、Claude containment 和 Series H 融资放回 AI Agent 自进化主题:模型竞争正在变成 AgentOps 基础设施竞争。

📝 博客 博客

Agent 框架不是自进化:AutoGPT、MetaGPT、AutoGen、CrewAI、DSPy、LangGraph 差在哪

从英文论文第六章拆解主流 Agent 框架:它们提供运行时、角色、对话、流程、prompt 编译或状态图,但自进化需要额外的评估、记忆、更新和治理层。

📝 博客 博客

自进化 Agent 怎么评估:别只看分数,要看改进是否可复现

从英文论文第五章拆解自进化 AI 的评估问题:代码、数学、Agent、开放式 benchmark、Star 传播信号、过程指标和推荐评估协议。

📝 博客 博客

进化式代码与算法发现:为什么 AlphaEvolve、DGM 和 OpenEvolve 重要

从英文论文第四章拆解进化式代码和算法发现:LLM 作为优化器、语义变异器、程序搜索器,以及 AlphaEvolve、Darwin Gödel Machine、OpenEvolve 的工程意义。

📝 博客 博客

自进化 Agent 的五个循环:反馈、搜索、评估、反思与种群

从英文论文第二章拆解 Self Evolve 的 Five Evolution Loops:Specification-to-Execution、Search、Evaluator、Reflection、Population,以及如何组合成真实 Agent 系统。

📝 博客 博客

自进化 AI 的未来路线图:评估器、记忆、安全、组合性和生产治理

从英文论文第八章拆解未来方向:评估瓶颈、长期记忆漂移、安全与对齐、五大循环组合、生产挑战和 Self Evolve 两到三年路线图。

📝 博客 博客

AI Agent 自进化入门:从静态模型到会改进自己的系统

把 Self-Evolving AI Agents 英文论文第一章拆成一篇可读博客:解释什么是 AI 自进化、它和在线学习/AutoML/普通 Agent 的边界,以及为什么真正的问题是可验证的自我修改。

📝 博客 博客

LLM 自我改进方法全图:Self-Refine、Reflexion、RISE 到 Absolute Zero

从英文论文第三章拆解 LLM/Agent 自我改进方法:推理时修正、反思记忆、训练期自博弈、RL、语言梯度,以及什么时候该用 prompt、fine-tuning 或 reinforcement learning。

📝 博客 博客

用户真正痛的不是 Agent 不够聪明,而是不可靠、不可观测、不可控

从英文论文第七章拆解自进化 Agent 的用户痛点:幻觉、循环、工具误用、上下文溢出、调试困难、成本、部署、监控与治理。

📝 博客 博客

ADAS 到 DGM:智能体架构自动搜索的进化之路

追踪从 ADAS(ICLR 2025)到 Darwin Gödel Machine 的技术演进:从图灵完备搜索到开放式进化归档。UBC Jeff Clune 团队如何让 Agent 自己设计自己。

📝 博客 博客

Reflexion 深度解读:用语言反思替代参数更新

Reflexion 如何把任务失败转化为自然语言记忆,让 Agent 在不更新权重的情况下持续改进。

📝 博客 博客

AI 自我进化:从概念到实现的证据导读

什么是 AI Self Evolution?本文从 Self Evolve 视角梳理自我进化智能体的核心概念、技术路线与实现路径,帮助读者先建立可复核判断框架。

📝 博客 博客

什么是 AI 自我进化?一张面向开发者的地图

用工程视角梳理自进化智能体如何改进提示词、工具、记忆、代码、工作流与策略,并给出可变对象、反馈信号、验证门和回滚边界。

📝 博客 博客

AlphaEvolve 深度解析:从 MAP-Elites 到算法发现证据

分析 Google DeepMind AlphaEvolve 的双模型架构、MAP-Elites 质量多样性搜索和 4×4 complex-valued matrix multiplication 的 48-scalar result,并标出复核边界。

📝 博客 博客

代码自我改进:从智能体补丁到回归门禁

一套轻量实践流程:让编码智能体自调试、写测试、修复失败并重新验证,同时保留基线、回归切片、失败记录和可审计改进证据。

📝 博客 博客

AI 自我进化的跨领域图谱:从 AutoML 到 Agent 自修改

梳理 AutoML/NAS、进化计算、LLM 自我改进与 Agent 框架之间的深层连接,揭示 Self Evolve 的技术全景。

📝 博客 博客

进化计算 × 大语言模型:2024-2025 前沿导读

导读进化计算与 LLM 融合的代表性进展:从 OPRO、FunSearch 到 AlphaEvolve,从 LLaMEA 到 OpenEvolve。本文是阅读入口,不是系统综述协议。

📝 博客 博客

如何构建自我进化的 AI Agent:最小闭环设计笔记

面向开发者的 Self-Evolving Agent 构建笔记。从最小闭环开始,逐步添加评估器、记忆、进化策略和回归防护,并标出哪些环节仍需复核。

📝 博客 博客

LLM 即优化器:从 OPRO 到 FunSearch 的进化式编码

解读 OPRO、FunSearch、ReEvo 和 LLaMEA 四篇核心论文,理解 LLM 如何充当变异器、重组器和候选生成器。

📝 博客 博客

LLM 自我改进的五种范式:从 Self-Refine 到 Absolute Zero

对比分析 Self-Refine、Reflexion、Agent Symbolic Learning、RISE 和 Absolute Zero 五种 LLM 自我改进范式的方法、优劣与适用场景。Self Evolve 核心技术解读。

📝 博客 博客

开源自进化 AI 项目巡礼:10 个可复核的仓库

从 Self Evolve 项目索引中选取 10 个覆盖不同机制的开源自进化 AI 项目,涵盖进化式代码优化、Agent 进化框架、反思记忆与自评判训练。本文说明它们适合回答什么问题,也标出证据边界。

📝 博客 博客

Self Evolve 研究者图谱:谁在推动 AI 自我进化

梳理 AI 自我进化领域的核心研究者、实验室与合作网络,从 Jeff Clune 的开放式进化到 Google DeepMind 的 AlphaEvolve。

📝 博客 博客

Self Evolve GitHub 项目索引如何阅读

从 OpenEvolve、AgentEvolver、Reflexion 到 Self-Refine,理解自进化 AI 项目的四类实现路线。

📝 博客 博客

SelfEvolve 论文深度解读:LLM 如何实现代码自我改进

详细解读 SelfEvolve 论文的方法、公式与实验结果。探索 LLM 自生成知识与迭代自调试如何实现代码自我改进,以及与 Self Evolve 生态的关联。