fast-agent Skills MCP ACP Runtime Model Card
这是可索引项目报告证据页：它保留 fast-agent Skills MCP ACP Runtime Model Card 的源材料入口、机制线索和限制提醒；正文仍需 reader/editor 与 academic public-copy review 后才能当作最终结论引用。
fast-agent Skills MCP ACP Runtime Model Card
| Field | Value |
|---|---|
| Repository | evalstate/fast-agent |
| Category | Skills/MCP/ACP Agent Runtime |
| Stars / forks snapshot | 3800 / 404 |
| Language | Python |
| License | Apache-2.0 |
| Raw capture | raw-github/evalstate_fast-agent.md |
| Updated by | hourly public metadata update, 2026-05-25 |
1. Role in Self Evolve
fast-agent 是面向编码、构建和评测 Agent 的 Python 运行时，集成 SKILL.md、MCP、ACP、shell 模式、/skills 管理和 /connect 工具连接。
2. Working Principle
fast-agent CLI/TUI -> Skills registry -> MCP/ACP connections -> coding/evaluation workflow runtime
3. Evidence Path
web GitHub page observed 1,837 commits, Apache-2.0 license, 3.8k stars and 404 forks, 88 releases with v0.7.7 latest on 2026-05-19, Python 98.6%; README says fast-agent is a coding agent, development toolkit, evaluation and workflow platform, supports uvx fast-agent-mcp —pack codex, /skills command, /connect for MCP servers, shell mode, Agent Skills, MCP-UI, OpenAI Apps SDK, OAuth transport diagnostics, and ACP/MCP topics. Shell GitHub API access remained blocked by DNS and local gh auth was invalid in this run, so this card treats the current snapshot as web-observed rather than API-verified.
4. Teaching Use
Use this card to explain Skills/MCP/ACP Agent Runtime in the raw -> classification -> project card -> site/report pipeline. The reading path is: raw capture -> classification row -> public site card -> project report -> aggregate GitHub analysis.
5. Limits
当前未克隆源码，未运行 benchmark、skill install flows、memory experiments、MCP servers、agent evolution loops、security scanners 或 production deployments；star/fork/commit/release 快照来自公开 GitHub 页面文本或可见页面片段。