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 normalized popularity across sources. 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

    Vane is an AI-powered answering engine.

    TypeScriptLicense: MIT
    • ai-agents
    • ai-search-engine
    • answering-engine
    • artificial-intelligence
    • llm

    githubestimated momentumOpen source ↗

    36 578GitHub stars—
  2. 2

    Skill
    Active

    Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

    PythonLicense: MIT
    • agent-skills
    • ai-agents
    • book-to-skill
    • context-engineering
    • document-processing

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/virgiliojr94/book-to-skill ~/.claude/skills/book-to-skill

    27 824GitHub stars+1 525 (+5.8 %)
  3. 3

    Skill
    Active

    A lightweight, lightning-fast, in-process vector database

    C++License: Apache-2.0
    • agent-skills
    • db
    • embedded
    • faiss
    • fts

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/alibaba/zvec ~/.claude/skills/zvec

    15 591GitHub stars+62 (+0.40 %)
  4. 4

    MCP
    Active

    🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

    PythonLicense: GPL-3.0
    • agent
    • agentic-ai
    • chatbot
    • deepseek-r1
    • knowledgebase

    githubmeasured growthOpen source ↗

    22 693GitHub stars+58 (+0.26 %)
  5. 5

    Other
    Active

    Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

    JavaScriptLicense: MIT
    • agent-computer
    • agent-harness
    • agent-orchestration
    • agentic-ai
    • ai-agents

    githubmeasured growthOpen source ↗

    65 486GitHub stars+178 (+0.27 %)
  6. 6

    Other
    Active

    【低代码v2.0，一句话即可生成整个系统】企业级AI低代码平台，一键生成前后端代码甚至整个系统。 AI Skills 一句话画流程、设计表单、生成报表、大屏。内置 AI应用平台涵盖：AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领AI低代码「Skills 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，解决 Java 项目 90% 重复工作，提高效率又不失灵活。

    JavaLicense: Apache-2.0
    • activiti
    • agent
    • ai
    • antd
    • claude-code

    githubmeasured growthOpen source ↗

    47 595GitHub stars+89 (+0.19 %)
  7. 7

    Skill
    Active

    Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

    PythonLicense: Apache-2.0
    • agent-memory
    • agent-skills
    • ai
    • ai-agents
    • ai-memory

    githubmeasured growthOpen source ↗

    Install git clone https://github.com/topoteretes/cognee ~/.claude/skills/cognee

    30 405GitHub stars+105 (+0.35 %)
  8. 8

    Library
    UnknownLast commit: unavailable

    Embeddings, Retrieval, and Reranking

    • Transformer Networks
    • BERT
    • XLNet
    • sentence embedding
    • PyTorch

    pypimeasured growthOpen source ↗

    Install pip install sentence-transformers

    5 313 257downloads over 7 days-1 809 510 (-25.4 %)
  9. 9

    Other
    Active

    Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.

    Rust
    • ai
    • bigdata
    • cloud-native
    • database
    • elasticsearch

    githubmeasured growthOpen source ↗

    9 433GitHub stars+9 (+0.10 %)
  10. 10

    Library
    UnknownLast commit: unavailable

    Interface between LLMs and your data

    • LLM
    • NLP
    • RAG
    • data
    • devtools

    pypimeasured growthOpen source ↗

    Install pip install llama-index

    762 620downloads over 7 days-556 575 (-42.2 %)
  11. 11

    MCP
    Active

    Semantic search across Sui documentation and knowledge sources, powered by kapa.ai

    RustLicense: Apache-2.0

      mcpmeasured growthOpen source ↗

      Remote server, to be declared in the MCP configuration https://sui.mcp.kapa.ai

      7 740GitHub stars+2 (+0.03 %)
    • 12

      MCP
      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。

      PythonLicense: MIT
      • agentic-ai
      • agentic-workflows
      • ai-agent
      • ai-agents
      • awesome-list

      githubmeasured growthOpen source ↗

      6 589GitHub stars+144 (+2.2 %)
    • 13

      Other
      Active

      High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

      RustLicense: Apache-2.0
      • ai-engineering
      • ai-pipeline
      • arrow
      • artificial-intelligence
      • big-data

      githubmeasured growthOpen source ↗

      5 736GitHub stars+5 (+0.09 %)
    • 14

      Agent
      Active

      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.

      PythonLicense: Apache-2.0
      • a2a
      • agentframework
      • agentic
      • agentic-ai
      • agentic-framework

      githubmeasured growthOpen source ↗

      4 950GitHub stars-2 (-0.04 %)
    • 15

      Other
      Active

      CrateDB is a distributed and scalable SQL database for storing and analyzing massive amounts of data in near real-time, even with complex queries. It is PostgreSQL-compatible, and based on Lucene.

      JavaLicense: Apache-2.0
      • analytics
      • big-data
      • cratedb
      • database
      • dbms

      githubmeasured growthOpen source ↗

      4 432GitHub stars+3 (+0.07 %)
    • 16

      Skill
      Active

      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,…

      PythonLicense: MIT
      • agent-skills
      • ai-agents
      • ai-note-taking
      • ai-second-brain
      • anthropic

      githubmeasured growthOpen source ↗

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

      4 292GitHub stars+66 (+1.6 %)
    • 17

      Agent
      Active

      Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3.…

      JavaLicense: Apache-2.0
      • a2a
      • acp
      • agentic-ai
      • ai-agents
      • anthropic

      githubmeasured growthOpen source ↗

      3 804GitHub stars+8 (+0.21 %)
    • 18

      Agent
      Active

      AI-powered virtual executive team — a single coherent executive persona backed by 8 specialist Claude agents (FastAPI + Next.js).

      Python
      • ai
      • anthropic
      • claude
      • fastapi
      • llm

      githubmeasured growthOpen source ↗

      3 488GitHub stars+1 925 (+123.2 %)
    • 19

      MCP
      Active

      MCP server for local codebase indexing, semantic search, and code dependency graphs.

      ↓ 1 242 downloads/weekTypeScriptLicense: AGPL-3.0

        mcpmeasured growthOpen source ↗

        Install claude mcp add socraticode -- npx socraticode

        3 275GitHub stars+12 (+0.37 %)
      • 20

        Library
        Active

        LakeSoul is an end-to-end, realtime cloud-native Lakehouse framework for fast data ingestion, concurrent updates, incremental analytics, multimodal data processing and vector search — powering next-generation BI and AI workloads.

        JavaLicense: Apache-2.0
        • arrow
        • daft
        • datafusion
        • flink
        • gluten

        githubmeasured growthOpen source ↗

        3 249GitHub stars+2 (+0.06 %)
      • 21

        Skill
        Active

        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.

        PythonLicense: Apache-2.0
        • agent-skills
        • agentic-ai
        • ai-agents
        • claude-code
        • codex

        githubmeasured growthOpen source ↗

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

        3 172GitHub stars+53 (+1.7 %)
      • 22

        MCP
        Active

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

        PythonLicense: Apache-2.0

          mcpmeasured growthOpen source ↗

          Install claude mcp add arxiv-mcp-server -- uvx arxiv-mcp-server

          3 091GitHub stars+26 (+0.85 %)
        • 23

          Skill
          Active

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

          PythonLicense: MIT
          • agent
          • agent-memory
          • ai-agents
          • claude-code
          • claude-code-plugin

          githubmeasured growthOpen source ↗

          Install /plugin marketplace add zilliztech/memsearch

          2 546GitHub stars+27 (+1.1 %)
        • 24

          App
          Active

          World's first open-source enterprise world model.

          RustLicense: Apache-2.0
          • agent-memory
          • bitemporal
          • graphrag
          • knowledge-base
          • knowledge-graph

          githubmeasured growthOpen source ↗

          2 428GitHub stars+1 596 (+191.8 %)

        Learning resources

        Ranked by normalized popularity across sources. These resources remain available separately and do not take part in the main tool ranking.

        1. 1

          ai-engineering-hub

          Agent
          ActiveOpen source ↗

          In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

          Jupyter NotebookLicense: MIT
          • agents
          • ai
          • llms
          • machine-learning
          • mcp
          githubResourcemeasured growth
          37 263GitHub stars+63 (+0.17 %)