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

154 entries in this view.

Tool ranking

Ranked by creation date, newest first; undated entries come last. 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

    MCP
    Active

    Six-agent system for customer support, employee Q&A, and ops workflows — same LangGraph agents runnable under two interchangeable transports: Anthropic MCP and Google A2A. Live demo on HuggingFace Spaces.

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  2. 2

    MCP
    Dormant

    Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

    mcpmeasured growthOpen source ↗

    1GitHub starsstable
  3. 3

    Skill
    Active

    Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add XBlueSky/cortexes

    20GitHub starsstable
  4. 4

    MCP
    Active

    Fully local, zero-cost RAG knowledge layer for AI coding tools. Achieve near perfect codebase awareness with any AI tool. Supports Claude Code, Cursor, Codex, Antigravity

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  5. 5

    Skill
    Active

    Your AI confers, with anyone's — an open A2A protocol platform where AI Agents talk to each other on behalf of their owners. Self-hosted, DID:web identity, RFC 9421 signatures, Claude Code plugin.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/hyhmrright/Confer ~/.claude/skills/Confer

    3GitHub starsstable
  6. 6
    Active

    Curated skill pack for LLM agents in engineer and science workflow (Cursor & Claude ready).

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/charlieviettq/awesome-agent-skill ~/.claude/skills/awesome-agent-skill

    25GitHub starsstable
  7. 7
    Active

    Local NotebookLM for Claude Code via Google Antigravity (agy / Gemini 3.x): /agy:notebook turns a folder of documents into per-doc summaries + a relevance index + a cited synthesis + Q&A. Plus audio/video transcription, deep web research…

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add MarcosNahuel/antigravity-plugin-cc

    26GitHub starsstable
  8. 8

    Agent
    Active

    Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decisions.

    githubmeasured growthOpen source ↗

    25GitHub starsstable
  9. 9
    Active

    Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project…

    githubmeasured growthOpen source ↗

    7GitHub starsstable
  10. 10

    Skill
    Active

    Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation…

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/Socialpranker/deepdive ~/.claude/skills/deepdive

    393GitHub stars+5 (+1.3 %)
  11. 11
    Dormant

    D&D AI game master built with Strands SDK — multi-agent orchestration using MCP, A2A protocol, and RAG-based rules lookup

    githubmeasured growthOpen source ↗

    2GitHub starsstable
  12. 12
    Active

    Claude Code plugin: four-layer long-term memory (L0→L1→L2→L3 Persona) with local FTS5 + EmbeddingGemma vector hybrid recall, zero external API

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add baodq97/tencentdb-agent-memory

    10GitHub starsstable
  13. 13
    Active

    全流程 智能招投标 Agent:标书生成 · 招投标解读 · 标书检查 · 标书文档ai排版 · 商机发现 一键完成。 21 项合规检查 · 多模型切换 · RAG 知识库 · OCR 抽取。 从招标公告到可交付 docx 文档,全流程 AI 自动化。

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/guangshu100/BidMaster-Pro ~/.claude/skills/BidMaster-Pro

    251GitHub stars+30 (+13.6 %)
  14. 14

    Agent
    Dormant

    Production multi-agent IT/HR service platform — LangGraph + DSPy + RAG resolves enterprise tickets autonomously with A2A protocol support

    githubmeasured growthOpen source ↗

    1GitHub starsstable
  15. 15
    Active

    MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access.

    mcpmeasured growthOpen source ↗

    Install claude mcp add mcp-db-connect -- npx mcp-db-connect

    1GitHub starsstable
  16. 16
    Dormant

    A2A-compliant agent template built on LangChain's create_agent() with tool-calling. Define your tools, get a working A2A endpoint with agent discovery, task lifecycle, and JSON-RPC out of the box. Includes optional Qdrant vector store for…

    githubmeasured growthOpen source ↗

    0GitHub starsstable
  17. 17
    Active

    Open-source preview of *Claude Code for AI Engineers* - a methodology-first skill pack for RAG eval, agent debugging, MCP servers, paper reproduction, and benchmark reporting. Full pack (6 skills, 3 templates, 5 slash commands) at…

    githubmeasured growthOpen source ↗

    2GitHub starsstable
  18. 18

    Skill
    Active

    Turn scattered knowledge, operational data, and history into source-linked context that your agents can inspect, explain, and reuse.

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/sparkplug604/praxis ~/.claude/skills/praxis

    48GitHub starsstable
  19. 19
    Dormant

    Enterprise-grade database architect, security auditor and production consultant for Supabase — Claude Code Skill

    githubmeasured growthOpen source ↗

    3GitHub starsstable
  20. 20
    Active

    SHM v6.15.0 — 自演化超图记忆系统: R4OracleDb oracle DB 同形注入, 评测数据面重建 (LoCoMo-Refined 72.43%), 精卫循环至 SOTA 82.65 进行中

    githubmeasured growthOpen source ↗

    6GitHub starsstable
  21. 21
    Dormant

    Knowledge API for AI agents — content, agent directory, model benchmarks, semantic search.

    mcpmeasured growthOpen source ↗

    Install claude mcp add voidfeed-mcp -- npx voidfeed-mcp

    0GitHub starsstable
  22. 22

    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。

    githubmeasured growthOpen source ↗

    59GitHub stars+2 (+3.5 %)
  23. 23
    Active

    A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

    githubmeasured growthOpen source ↗

    6 659GitHub stars+154 (+2.4 %)
  24. 24

    MCP
    Dormant

    RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.

    mcpmeasured growthOpen source ↗

    Remote server, to be declared in the MCP configuration https://redm-mcp.fivem.no/mcp

    3GitHub starsstable

Learning resources

Ranked by creation date, newest first; undated entries come last. These resources remain available separately and do not take part in the main tool ranking.

  1. 1
    ActiveOpen source ↗

    Handbook técnico aberto sobre engenharia de IA em produção: ML tradicional, LLMs, RAG, agentes, segurança, observabilidade, FinOps e deployment.

    githubResourcemeasured growth
    1GitHub starsstable