跳转至

GitHub 宝藏挖掘 - 2026-09-20

Top 5

1. DeusData/codebase-memory-mcp (43,848⭐) [🔴]

  • Score: 88/100 | Lang: C | License: MIT
  • High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary
  • URL: https://github.com/DeusData/codebase-memory-mcp

2. HKUDS/nanobot (48,375⭐) [🔴]

  • Score: 81/100 | Lang: Python | License: MIT
  • Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
  • URL: https://github.com/HKUDS/nanobot

3. tirth8205/code-review-graph (31,623⭐) [🔴]

  • Score: 74/100 | Lang: Python | License: MIT
  • Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w
  • URL: https://github.com/tirth8205/code-review-graph

4. ChromeDevTools/chrome-devtools-mcp (52,339⭐) [🟡]

  • Score: 69/100 | Lang: TypeScript | License: Apache-2.0
  • Chrome DevTools for coding agents
  • URL: https://github.com/ChromeDevTools/chrome-devtools-mcp

5. langgenius/dify (156,522⭐) [🟡]

  • Score: 62/100 | Lang: TypeScript | License: NOASSERTION
  • Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without reb
  • URL: https://github.com/langgenius/dify

MCP 生态发现

  • DeusData/codebase-memory-mcp (88/100): High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-
  • HKUDS/nanobot (81/100): Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, a
  • tirth8205/code-review-graph (74/100): Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmar

洞察

  1. MCP 持续成为 Agent 标准接口
  2. 本地优先是主流趋势
  3. 记忆系统是核心突破点

自动生成 2026-09-20 14:25

🗺️ 属于 [[MOC-Research]] · [[Home|🏠 Home]]