RAG and search: tools for developers

Retrieval-augmented tools, vector databases, embeddings and semantic search. An entry can appear under several use cases when its topics or description provide several explicit signals.

Use case

Activity

Sort by

139 entries in this view.

Tool ranking

Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.

  1. 1

    Agent
    Active

    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。

    Kotlin
    • a2a
    • ai-agent
    • human-in-the-loop
    • rag
    • stategraph

    githubmeasured growthOpen source ↗

    100GitHub stars-1 (-0.99 %)
  2. 2

    Skill
    Active

    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,…

    Python
    • agent-use-ready
    • ai-agents
    • claude-code
    • claude-skills
    • doc-converter

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/agentii-ai/DocMeld ~/.claude/skills/DocMeld

    100GitHub starsstable
  3. 3

    Skill
    Active

    Andrej Karpathy's LLM Wiki pattern as a skill & Claude Code plugin — turn accumulated sources into a self-maintaining, scalable markdown knowledge base.

    TypeScriptLicense: MIT
    • ai-tools
    • claude-code-plugin
    • claude-code-skill
    • codex-skill
    • cursor

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add praneybehl/llm-wiki-plugin

    99GitHub stars+5 (+5.3 %)
  4. 4

    Agent
    Active

    🚀 Way Back Home

    PythonLicense: Apache-2.0
    • a2a
    • adk
    • agents
    • bigquery
    • google-cloud

    githubmeasured growthOpen source ↗

    96GitHub starsstable
  5. 5

    Skill
    Active

    Distill any document corpus into a navigable skill hierarchy for LLM agents — no retrieval system needed at serve time.

    PythonLicense: MIT
    • agent-skills
    • emnlp-2026
    • enterprise-search
    • llm
    • llm-agents

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/dukesun99/Corpus2Skill ~/.claude/skills/Corpus2Skill

    84GitHub stars+1 (+1.2 %)
  6. 6

    Skill
    Active

    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,…

    PythonLicense: MIT
    • agentic-ai
    • ai-agents
    • claude
    • claude-code
    • claude-skills

    githubmeasured growthOpen source ↗

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

    81GitHub stars+1 (+1.2 %)
  7. 7

    MCP
    Active

    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.

    RustLicense: MIT
    • ast
    • call-graph
    • claude-code
    • claude-code-plugin
    • code-navigation

    githubmeasured growthOpen source ↗

    72GitHub stars+2 (+2.9 %)
  8. 8

    MCP
    Active

    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.…

    PythonLicense: MIT
    • agent-memory-system
    • agent-skills
    • causal-inference
    • claude-code
    • codex

    githubmeasured growthOpen source ↗

    71GitHub starsstable
  9. 9

    Skill
    Active

    The official Pinecone marketplace for Claude Code Plugins

    PythonLicense: MIT
    • anthropic-claude
    • claude-code
    • claude-code-plugin
    • claude-code-plugin-marketplace
    • hybrid-search

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add pinecone-io/pinecone-claude-code-plugin

    68GitHub starsstable
  10. 10

    Skill
    Active

    Semantic Scholar API wrapper for agents — search 200M+ papers, traverse citations, find authors. Python, rate-limited, multi-agent.

    PythonLicense: MIT
    • academic
    • agent-skill
    • agent-skills
    • citations
    • claude-code

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/Agents365-ai/semanticscholar-skill ~/.claude/skills/semanticscholar-skill

    68GitHub starsstable
  11. 11

    MCP
    Active

    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

    PythonLicense: MIT
    • ai-memory
    • ai-tools
    • anthropic
    • chromadb
    • claude-code

    githubmeasured growthOpen source ↗

    67GitHub stars+1 (+1.5 %)
  12. 12

    MCP
    Active

    Local-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud.

    RustLicense: MIT

      mcpmeasured growthOpen source ↗

      67GitHub starsstable
    • 13

      MCP
      Active

      Token-efficient code review knowledge graph: semantic search and call-graph resolution.

      PythonLicense: Apache-2.0

        mcpmeasured growthOpen source ↗

        Install claude mcp add better-code-review-graph -- uvx better-code-review-graph

        66GitHub starsstable
      • 14

        MCP
        Active

        RuvNet 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),…

        JavaScript
        • agentdb
        • ai-agents
        • anthropic-claude
        • claude-code
        • claude-code-plugin

        githubmeasured growthOpen source ↗

        65GitHub stars+1 (+1.6 %)
      • 15

        Skill
        Active

        Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants

        License: MIT
        • ade
        • agent-skills
        • claude
        • document-extraction
        • document-processing

        githubmeasured growthOpen source ↗

        Install git clone https://github.com/landing-ai/ade-document-processing-skills ~/.claude/skills/ade-document-processing-skills

        64GitHub starsstable
      • 16

        MCP
        Active

        Semantic search and pattern discovery for Obsidian and markdown vaults.

        TypeScript

          mcpmeasured growthOpen source ↗

          59GitHub starsstable
        • 17

          Agent
          Active

          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。

          Python
          • agentic-ai
          • claim-chart
          • claude-code
          • claude-code-skill
          • codex

          githubmeasured growthOpen source ↗

          59GitHub stars+2 (+3.5 %)
        • 18

          Other
          Active

          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…

          RustLicense: MIT
          • a2a
          • acp
          • ai-agent
          • claude
          • cli

          githubmeasured growthOpen source ↗

          58GitHub stars+1 (+1.8 %)
        • 19

          MCP
          Active

          Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search, tag graph, MCP memory.

          TypeScriptLicense: Apache-2.0
          • agent-skills
          • ai-memory
          • ai-tools
          • claude-code
          • codex

          githubmeasured growthOpen source ↗

          58GitHub stars+3 (+5.5 %)
        • 20

          MCP
          Active

          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…

          JavaScriptLicense: MIT
          • agent-memory
          • ai-coding-assistant
          • ai-memory
          • anthropic
          • claude

          githubmeasured growthOpen source ↗

          57GitHub stars+3 (+5.6 %)
        • 21

          Skill
          Active

          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…

          PythonLicense: MIT
          • agent-memory
          • agent-skills
          • agentic-workflow
          • agents
          • anthropic

          githubmeasured growthOpen source ↗

          Install git clone https://github.com/firish/webfetch ~/.claude/skills/webfetch

          55GitHub starsstable
        • 22

          MCP
          Active

          Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.

          TypeScriptLicense: MIT

            mcpmeasured growthOpen source ↗

            Install claude mcp add smart-connections-mcp -- npx smart-connections-mcp

            54GitHub starsstable
          • 23

            Skill
            Active

            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.

            PythonLicense: MIT
            • agent
            • agent-skills
            • agentic-workflow
            • langgraph
            • llm

            githubmeasured growthOpen source ↗

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

            50GitHub starsstable
          • 24

            MCP
            Dormant

            Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.

            PythonLicense: MIT
            • ai-tools
            • autonomous-agent
            • claude-code
            • claude-code-plugin
            • fastapi

            githubmeasured growthOpen source ↗

            49GitHub starsstable

          Learning resources

          Ranked by known GitHub stars, highest first; archived repositories come after maintained repositories. These resources remain available separately and do not take part in the main tool ranking.

          1. 1

            membrane

            Skill
            ActiveOpen source ↗

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

            GoLicense: MIT
            • agent
            • agent-framework
            • agent-memory
            • agent-skills
            • agentic
            github

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

            Resourcemeasured growth
            94GitHub starsstable