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

138

工具排名

按实测增长排序,并在不同来源间归一化。 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. 1

    技能
    活跃

    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/webfetch

    55GitHub 星标稳定
  2. 2

    MCP
    活跃

    Semantic search and pattern discovery for Obsidian and markdown vaults.

    mcp实测增长打开来源 ↗

    59GitHub 星标稳定
  3. 3

    技能
    活跃

    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/DocMeld

    100GitHub 星标稳定
  4. 4
    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-skills

    64GitHub 星标稳定
  5. 5
    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-plugin

    68GitHub 星标稳定
  6. 6

    MCP
    活跃

    Cross-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
  7. 7

    智能体
    活跃

    🚀 Way Back Home

    github实测增长打开来源 ↗

    96GitHub 星标稳定
  8. 8

    智能体
    活跃

    An event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.

    github实测增长打开来源 ↗

    4 951GitHub 星标稳定
  9. 9

    MCP
    活跃

    Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

    github实测增长打开来源 ↗

    372GitHub 星标稳定
  10. 10
    活跃

    Local-first document management and semantic search for AI coding agents

    mcp实测增长打开来源 ↗

    安装 claude mcp add mcp-documentation-server -- npx @andrea9293/mcp-documentation-server

    342GitHub 星标稳定
  11. 11

    MCP
    活跃

    A semantic search engine for files and code.

    mcp实测增长打开来源 ↗

    安装 claude mcp add vexor -- uvx vexor

    239GitHub 星标稳定
  12. 12

    其他
    活跃

    Deploy intelligence. Open-source infrastructure for AI agents in production.

    github实测增长打开来源 ↗

    169GitHub 星标稳定
  13. 13

    技能
    活跃

    Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/hwfengcs/DM-Code-Agent ~/.claude/skills/DM-Code-Agent

    151GitHub 星标稳定
  14. 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-skill

    68GitHub 星标稳定
  15. 15
    活跃

    Pure instruction-pack skill wrapping Ai2's Asta MCP server (Semantic Scholar). Intent-to-tool routing, safe defaults, multi-agent.

    github实测增长打开来源 ↗

    183GitHub 星标稳定
  16. 16
    活跃

    A LangGraph-powered multi-agent deep research system featuring task planning, human-in-the-loop review, multi-source retrieval, evidence-grounded report generation, full tracing and reproducible evaluation.

    github实测增长打开来源 ↗

    安装 git clone https://github.com/hwfengcs/SDYJ_Multi_Agents ~/.claude/skills/SDYJ_Multi_Agents

    50GitHub 星标稳定
  17. 17
    未知最近提交:暂无数据

    Embeddings, Retrieval, and Reranking

    pypi实测增长打开来源 ↗

    安装 pip install sentence-transformers

    5 337 5017 天下载量-354 838 (-6.2 %)
  18. 18

    未知最近提交:暂无数据

    Typescript bindings for langchain

    npm实测增长打开来源 ↗

    安装 npm install langchain

    2 147 9957 天下载量-154 912 (-6.7 %)
  19. 19
    未知最近提交:暂无数据

    Interface between LLMs and your data

    pypi实测增长打开来源 ↗

    安装 pip install llama-index

    777 7457 天下载量-72 798 (-8.6 %)

学习与参考资源

按实测增长排序,并在不同来源间归一化。 这些资源可单独访问,不参与主要排名。

  1. 1

    membrane

    技能
    活跃打开来源 ↗

    A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

    github

    安装 git clone https://github.com/BennettSchwartz/membrane ~/.claude/skills/membrane

    资源实测增长
    94GitHub 星标稳定
  2. 2
    活跃打开来源 ↗

    A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.

    github

    安装 git clone https://github.com/kimtth/azure-openai-llm-notes ~/.claude/skills/azure-openai-llm-notes

    资源实测增长
    410GitHub 星标稳定
  3. 3
    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-1 (-0.32 %)
  4. 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 /plugin marketplace add johnzfitch/claude-wiki

    资源实测增长
    21GitHub 星标稳定
  5. 5
    活跃打开来源 ↗

    Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips

    github资源实测增长
    46GitHub 星标稳定
  6. 6
    活跃打开来源 ↗

    🤖 The strongest curated list of open-source AI-agent tools for literature review — 70+ tools across 11 categories (Claude Code skills, deep research, MCP servers, PDF parsing, systematic review). 面向智能体文献综述的最强工具大全。

    github资源实测增长
    16GitHub 星标+3 (+23.1 %)