工具说明为英文。
RAG 与搜索
检索增强、向量数据库、嵌入和语义搜索。
用途
活跃度
排序方式
154
工具排名
Ranked by creation date, newest first; undated entries come last. 原始值保留各自的数据窗口；计算变化需要 7 天内至少两次测量。
- 1活跃
Local-first second brain with semantic search. Markdown notes indexed by a local ML model.
mcp实测增长打开来源 ↗
安装
claude mcp add memex -- npx @evan-moon/memex3GitHub 星标稳定 - 2活跃
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
github实测增长打开来源 ↗
安装
git clone https://github.com/virgiliojr94/book-to-skill ~/.claude/skills/book-to-skill28 556GitHub 星标+1 487 (+5.5 %) - 3休眠
Agent-as-a-Tool: An infinite-scale AI orchestration framework solving Tool Space Interference (TSI) via dynamic agent injection, RAG-based Agent Bank, and Zero-Trust execution using Google ADK.
github实测增长打开来源 ↗
3GitHub 星标稳定 - 4休眠
ZKshare
MCPZKshare stdio MCP: store/prove/share, semantic search, sandbox proxy to HTTPS /api/v1/context.
mcp实测增长打开来源 ↗
安装
claude mcp add zkshare -- npx zkshare-mcp0GitHub 星标稳定 - 5活跃
Nalegalu MCP
MCPSemantic search over Polish law and case law, citing the exact in-force article.
mcp实测增长打开来源 ↗
需在 MCP 配置中声明的远程服务器
https://mcp.nalegalu.org/mcp7GitHub 星标稳定 - 6活跃
High-performance knowledge graph MCP server for AI coding agents with semantic search.
mcp实测增长打开来源 ↗
安装
claude mcp add lain -- npx @spuentesp/lain-mcp6GitHub 星标稳定 - 7休眠
Federated Multi-Agent Real Estate System using A2A Protocol | LangGraph Orchestration | RAG Pipeline | ChromaDB | Groq LLaMA 3.1
github实测增长打开来源 ↗
0GitHub 星标稳定 - 8活跃
danwa
智能体Auditable multi-agent debate platform that uses AI agents to analyze, critique, and optimize arguments through structured deliberation.
github实测增长打开来源 ↗
0GitHub 星标稳定 - 9休眠
Embgrep
MCPLocal semantic search — embedding-powered grep for files, zero external services.
mcp实测增长打开来源 ↗
安装
claude mcp add embgrep -- uvx embgrep0GitHub 星标稳定 - 10活跃
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
mcp实测增长打开来源 ↗
安装
claude mcp add obsidian-brain -- npx obsidian-brain10GitHub 星标稳定 - 11活跃
webfetch
技能Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-tuned semantic caching with…
github实测增长打开来源 ↗
安装
git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch55GitHub 星标稳定 - 12活跃
graphify
技能Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
github实测增长打开来源 ↗
安装
git clone https://github.com/Graphify-Labs/graphify ~/.claude/skills/graphify114 805GitHub 星标+2 468 (+2.2 %) - 13活跃
headroom
MCPCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
github实测增长打开来源 ↗
68 952GitHub 星标+925 (+1.4 %) - 14活跃
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini,…
github实测增长打开来源 ↗
安装
/plugin marketplace add thedotmack/claude-mem93 211GitHub 星标+617 (+0.67 %) - 1512 013GitHub 星标+748 (+6.6 %)
- 1611 468GitHub 星标+36 (+0.31 %)
学习与参考资源
Ranked by creation date, newest first; undated entries come last. 这些资源可单独访问，不参与主要排名。
- 1休眠打开来源 ↗
Interactive roadmap for becoming an Agentic AI Engineer — 11 stages from Python & FastAPI to multi-agent systems, MCP, RAG, Docker, and context engineering
github资源实测增长1GitHub 星标稳定 - 2活跃打开来源 ↗
A practical AI agents handbook covering agent systems, agentic workflows, LangGraph, MCP/A2A, context engineering, agent memory, evaluation, observability, and multi-agent architecture. Current trend focus: Gemini Interactions API and…
github资源实测增长316GitHub 星标+3 (+0.96 %) - 3活跃打开来源 ↗
Detect underpriced products by scraping deals and using AI models to estimate fair prices for profit opportunity identification.
github资源实测增长1GitHub 星标稳定 - 4活跃打开来源 ↗
Official Claude Documentation - Converted to 2000+ Markdown Files - All documentation sourced from first party sources- 24 categories - refreshed daily, multi-agent orchestration
github安装
资源实测增长/plugin marketplace add johnzfitch/claude-wiki21GitHub 星标稳定 - 5休眠打开来源 ↗
Persistent memory for Claude Code. Auto-capture decisions, learnings, client info. Cloud backup to Supabase. Never lose context again. Free alternative to Mem.ai, Rewind AI, Personal AI.
github资源实测增长14GitHub 星标稳定 - 6活跃打开来源 ↗
membrane
技能A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
github安装
资源实测增长git clone https://github.com/BennettSchwartz/membrane ~/.claude/skills/membrane94GitHub 星标稳定 - 7活跃打开来源 ↗
Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically
github安装
资源实测增长git clone https://github.com/OmidZamani/dspy-skills ~/.claude/skills/dspy-skills122GitHub 星标+1 (+0.83 %) - 8活跃打开来源 ↗
Comprehensive collection of AI concepts, research findings, and practical implementations. From machine learning fundamentals to cutting-edge LLMs, agents, and emerging technologies.
github资源实测增长1GitHub 星标稳定 - 92GitHub 星标稳定