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

112

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

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

    Python许可证: Apache-2.0
    • agent-skills
    • agentic-ai
    • ai-agents
    • claude-code
    • codex

    github实测增长打开来源 ↗

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

    3 172GitHub 星标+53 (+1.7 %)
  2. 2

    技能
    活跃

    Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Stop re-explaining your projects, decisions and people every session. 45 commands: hybrid semantic search, self-rewriting notes,…

    Python许可证: MIT
    • agent-skills
    • ai-agents
    • ai-note-taking
    • ai-second-brain
    • anthropic

    github实测增长打开来源 ↗

    安装 git clone https://github.com/eugeniughelbur/obsidian-second-brain ~/.claude/skills/obsidian-second-brain

    4 292GitHub 星标+66 (+1.6 %)
  3. 3

    MCP
    活跃

    Search your past AI coding sessions — Claude Code, Codex, Cursor and 17 more. Indexes the session history they already wrote to disk, including months from before you installed it, and recalls it in any of them. No LLM, no embeddings, one…

    Go许可证: MIT
    • agent-memory
    • ai-memory
    • claude-code
    • claude-code-hooks
    • claude-code-plugins

    github实测增长打开来源 ↗

    742GitHub 星标+11 (+1.5 %)
  4. 4

    MCP
    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.

    Rust许可证: MIT
    • ast
    • call-graph
    • claude-code
    • claude-code-plugin
    • code-navigation

    github实测增长打开来源 ↗

    71GitHub 星标+1 (+1.4 %)
  5. 5

    MCP
    活跃

    Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

    TypeScript许可证: MIT
    • agent-skills
    • cli-tool
    • developer-tools
    • hybrid-search
    • local-first

    github实测增长打开来源 ↗

    378GitHub 星标+5 (+1.3 %)
  6. 6

    技能
    活跃

    FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.

    Python许可证: MIT
    • agent-skills
    • ai-persona
    • bdrc
    • buddhism
    • chinese-buddhism

    github实测增长打开来源 ↗

    安装 git clone https://github.com/xr843/Master-skill ~/.claude/skills/Master-skill

    380GitHub 星标+5 (+1.3 %)
  7. 7

    技能
    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,…

    Python许可证: MIT
    • agentic-ai
    • ai-agents
    • claude
    • claude-code
    • claude-skills

    github实测增长打开来源 ↗

    安装 git clone https://github.com/alfadur7/llm-wiki-newsroom ~/.claude/skills/llm-wiki-newsroom

    80GitHub 星标+1 (+1.3 %)
  8. 8

    技能
    活跃
    Python
    • agent
    • agent-memory
    • agent-skills
    • agentic
    • dsh-plugin

    github实测增长打开来源 ↗

    安装 git clone https://github.com/mindscale-noah/MindMemOS ~/.claude/skills/MindMemOS

    970GitHub 星标+12 (+1.3 %)
  9. 9

    MCP
    活跃

    Universal MCP Server with advanced AI memory capabilities and semantic search.

    ↓ 913 下载/周Python许可证: Apache-2.0

      mcp实测增长打开来源 ↗

      安装 claude mcp add marm-mcp-server -- uvx marm-mcp-server

      339GitHub 星标+4 (+1.2 %)
    • 10

      MCP
      活跃

      Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

      TypeScript许可证: MIT
      • accuracy
      • agents
      • claude-skills
      • context
      • harness

      github实测增长打开来源 ↗

      433GitHub 星标+5 (+1.2 %)
    • 11

      MCP
      活跃

      Compress 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.

      Python许可证: Apache-2.0
      • agent
      • ai
      • anthropic
      • claude-code
      • compression

      github实测增长打开来源 ↗

      68 629GitHub 星标+784 (+1.2 %)
    • 12

      MCP
      活跃

      USPTO patent creation system with MCP server + Claude Code plugin. Hybrid RAG search over MPEP/USC/CFR, BigQuery access to 76M+ patents, automated 35 USC 112 compliance checks, prior art search, diagram generation. GPU-accelerated with…

      Python许可证: MIT
      • bigquery
      • claude-code
      • claude-code-plugin
      • faiss
      • mcp-server

      github实测增长打开来源 ↗

      177GitHub 星标+2 (+1.1 %)
    • 13

      技能
      活跃

      A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

      Python许可证: MIT
      • agent
      • agent-memory
      • ai-agents
      • claude-code
      • claude-code-plugin

      github实测增长打开来源 ↗

      安装 /plugin marketplace add zilliztech/memsearch

      2 546GitHub 星标+27 (+1.1 %)
    • 14

      MCP
      活跃

      A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.

      Go许可证: Apache-2.0
      • a2a
      • a2a-protocol
      • ag-ui
      • agent
      • agent-framework

      github实测增长打开来源 ↗

      1 759GitHub 星标+18 (+1.0 %)
    • 15

      MCP
      活跃

      MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration

      TypeScript许可证: MIT
      • ai-agents
      • claude
      • claude-ai
      • claude-code
      • claude-code-plugin

      github实测增长打开来源 ↗

      102GitHub 星标+1 (+0.99 %)
    • 16

      MCP
      活跃

      Self improving agents through iterations

      Python许可证: Apache-2.0
      • agent-learning
      • agent-memory
      • agentic-workflows
      • ai-agents
      • claude-code

      github实测增长打开来源 ↗

      105GitHub 星标+1 (+0.96 %)
    • 17

      MCP
      活跃

      Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.

      Python许可证: Apache-2.0

        mcp实测增长打开来源 ↗

        安装 claude mcp add arxiv-mcp-server -- uvx arxiv-mcp-server

        3 091GitHub 星标+26 (+0.85 %)
      • 18

        MCP
        活跃

        A semantic search engine for files and code.

        Python许可证: MIT

          mcp实测增长打开来源 ↗

          安装 claude mcp add vexor -- uvx vexor

          239GitHub 星标+2 (+0.84 %)
        • 19

          技能
          活跃

          Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under…

          Python许可证: MIT
          • agent-memory
          • ai
          • ai-agents
          • ai-memory
          • claude-code

          github实测增长打开来源 ↗

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

          123GitHub 星标+1 (+0.82 %)
        • 20

          技能
          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,…

          JavaScript许可证: Apache-2.0
          • ai
          • ai-agents
          • ai-memory
          • anthropic
          • artificial-intelligence

          github实测增长打开来源 ↗

          安装 /plugin marketplace add thedotmack/claude-mem

          93 043GitHub 星标+717 (+0.78 %)
        • 21

          智能体
          活跃

          Ruby's capable AI runtime

          Ruby许可证: MIT
          • a2a
          • a2a-client
          • agent
          • agent2agent
          • agents

          github实测增长打开来源 ↗

          138GitHub 星标+1 (+0.73 %)
        • 22

          智能体
          活跃

          The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.

          Python许可证: Apache-2.0
          • agentic-memory
          • agentic-memory-system
          • agents
          • ai
          • ai-agents

          github实测增长打开来源 ↗

          64 602GitHub 星标+387 (+0.60 %)
        • 23

          智能体
          活跃

          RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

          Go许可证: Apache-2.0
          • agent-harness
          • agentic-ai
          • agentic-retrieval
          • agentic-search
          • ai

          github实测增长打开来源 ↗

          89 937GitHub 星标+518 (+0.58 %)

        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

          agent-systems-handbook

          智能体
          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…

          MDX
          • a2a
          • agent-framework
          • agent-memory
          • agentic-ai
          • agentic-workflow
          github资源实测增长
          316GitHub 星标+3 (+0.96 %)
        2. 2

          awesome-llm-apps

          技能
          活跃打开来源 ↗

          100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

          Python许可证: Apache-2.0
          • agents
          • llms
          • python
          • rag
          github

          安装 git clone https://github.com/Shubhamsaboo/awesome-llm-apps ~/.claude/skills/awesome-llm-apps

          资源实测增长
          135 793GitHub 星标+1 057 (+0.78 %)