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
142
工具排名
Ranked by normalized popularity across sources. 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
x402 pay-per-use IBM Granite AI: chat, code, embeddings, analysis, forecasting. Pay USDC per call.
mcp实测增长打开来源 ↗
安装
claude mcp add ibm-x402-mcp -- npx @three-ws/ibm-x402-mcp105GitHub 星标稳定 - 2活跃
LT2MD
技能AI-agent skill producing reusable Markdown from PDFs. It turns flowcharts, diagrams, and charts into text beside each caption instead of empty links. It checks an earlier conversion against the PDF and fixes misread or missing parts. Long…
github实测增长打开来源 ↗
安装
git clone https://github.com/libnyx/LT2MD ~/.claude/skills/LT2MD104GitHub 星标+45 (+76.3 %) - 3活跃
trace-mcp
MCPMCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration
github实测增长打开来源 ↗
103GitHub 星标+2 (+2.0 %) - 4活跃
SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.
github实测增长打开来源 ↗
安装
git clone https://github.com/oneal2000/SR-Agents ~/.claude/skills/SR-Agents102GitHub 星标+1 (+0.99 %) - 5活跃
Data-Agent：从 0 到 1 构建 Text2SQL 智能体实战教程，覆盖 StateGraph 编排、双重 RAG、关系图谱、HITL 人工确认、SQL 自动纠错、Python Docker 沙盒执行与 A2A + SSE 流式交互。
github实测增长打开来源 ↗
100GitHub 星标-1 (-0.99 %) - 6活跃
DocMeld
技能Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters,…
github实测增长打开来源 ↗
安装
git clone https://github.com/agentii-ai/DocMeld ~/.claude/skills/DocMeld100GitHub 星标稳定 - 7活跃
Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.
github实测增长打开来源 ↗
安装
/plugin marketplace add praneybehl/llm-wiki-plugin99GitHub 星标+5 (+5.3 %) - 896GitHub 星标稳定
- 9活跃
Distill any document corpus into a navigable skill hierarchy for LLM agents — no retrieval system needed at serve time.
github实测增长打开来源 ↗
安装
git clone https://github.com/dukesun99/Corpus2Skill ~/.claude/skills/Corpus2Skill84GitHub 星标+1 (+1.2 %) - 10活跃
Harness engineering applied to knowledge production: a self-evolving multi-agent newsroom that turns your documents into a cross-linked markdown wiki. A "reground" loop pulls published pages back in before they go stale — writer ≠ reviewer,…
github实测增长打开来源 ↗
安装
git clone https://github.com/alfadur7/llm-wiki-newsroom ~/.claude/skills/llm-wiki-newsroom80GitHub 星标+1 (+1.3 %) - 11活跃
AST knowledge graph MCP server for Claude Code — semantic search, call graph traversal, HTTP route tracing, impact analysis. Auto-indexes 10 languages via Tree-sitter.
github实测增长打开来源 ↗
72GitHub 星标+2 (+2.9 %) - 12活跃
Cortex
MCPCross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks.…
github实测增长打开来源 ↗
71GitHub 星标稳定 - 13活跃
The official Pinecone marketplace for Claude Code Plugins
github实测增长打开来源 ↗
安装
/plugin marketplace add pinecone-io/pinecone-claude-code-plugin68GitHub 星标稳定 - 14活跃
Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.
github实测增长打开来源 ↗
安装
git clone https://github.com/Agents365-ai/semanticscholar-skill ~/.claude/skills/semanticscholar-skill68GitHub 星标稳定 - 15活跃
Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud.
mcp实测增长打开来源 ↗
67GitHub 星标稳定 - 16活跃
Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional
github实测增长打开来源 ↗
67GitHub 星标+1 (+1.5 %) - 17活跃
Token-efficient code review knowledge graph: semantic search and call-graph resolution.
mcp实测增长打开来源 ↗
安装
claude mcp add better-code-review-graph -- uvx better-code-review-graph66GitHub 星标稳定 - 18活跃
ruvnet-brain
MCPRuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet),…
github实测增长打开来源 ↗
65GitHub 星标+1 (+1.6 %) - 19活跃
Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants
github实测增长打开来源 ↗
安装
git clone https://github.com/landing-ai/ade-document-processing-skills ~/.claude/skills/ade-document-processing-skills64GitHub 星标稳定 - 2059GitHub 星标+7 (+13.5 %)
- 21活跃
ChatCrystal
MCPLocal-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.
github实测增长打开来源 ↗
58GitHub 星标+3 (+5.5 %) - 22活跃
PatentRadar
智能体专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。
github实测增长打开来源 ↗
58GitHub 星标+1 (+1.8 %) - 23活跃
zeph
其他A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE. Graph memory, self-learning skills, multi-model routing, sandboxed…
github实测增长打开来源 ↗
57GitHub 星标稳定 - 24活跃
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem…
github实测增长打开来源 ↗
56GitHub 星标+2 (+3.7 %)
学习与参考资源
Ranked by normalized popularity across sources. 这些资源可单独访问，不参与主要排名。