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

147 entries in this view.

Tool ranking

Ranked by measured growth, normalized 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
    Dormant

    Agent registration, discovery, and reliable async messaging — in one broker.

    Python
    • a2a
    • a2a-protocol
    • a2discovery
    • agent
    • agent-communication

    githubmeasured growthOpen source ↗

    18GitHub stars+1 (+5.9 %)
  2. 2

    Skill
    Active

    Hivemind turns your traces into reusable skills across agents

    TypeScriptLicense: Apache-2.0
    • ai
    • ai-agents
    • ai-memory
    • anthropic
    • artificial-intelligence

    githubmeasured growthOpen source ↗

    Install /plugin marketplace add activeloopai/hivemind

    1 593GitHub stars+7 (+0.44 %)
  3. 3

    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 %)
  4. 4

    MCP
    Active

    Graph-powered code intelligence with semantic search and knowledge graph for AI assistants

    ↓ 107 downloads/weekTypeScriptLicense: NOASSERTION

      mcpmeasured growthOpen source ↗

      Install claude mcp add codeseeker -- npx codeseeker

      19GitHub stars+1 (+5.6 %)
    • 5

      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 %)
    • 6

      Skill
      Active

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

      PythonLicense: Apache-2.0
      • agent-memory
      • bm25
      • chromadb
      • claude-code
      • claude-code-plugin

      githubmeasured growthOpen source ↗

      Install /plugin marketplace add XBlueSky/cortexes

      20GitHub stars+1 (+5.3 %)
    • 7

      MCP
      Active

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

      ↓ 913 downloads/weekPythonLicense: Apache-2.0

        mcpmeasured growthOpen source ↗

        Install claude mcp add marm-mcp-server -- uvx marm-mcp-server

        339GitHub stars+4 (+1.2 %)
      • 8

        Agent
        Active

        BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level…

        PythonLicense: Apache-2.0
        • agent
        • ai
        • chatbot
        • enterprise
        • finetune

        githubmeasured growthOpen source ↗

        11 920GitHub stars+8 (+0.07 %)
      • 9

        Other
        Active

        The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.

        TypeScriptLicense: Apache-2.0
        • applicant-tracking-system
        • ats
        • hacktoberfest
        • machine-learning
        • natural-language-processing

        githubmeasured growthOpen source ↗

        28 302GitHub stars+8 (+0.03 %)
      • 10

        Other
        Active

        Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform - Providing a complete solution for agent creation and distribution, knowledge base management, model proxy, memory system, and plugin ecosystem.

        TypeScriptLicense: Apache-2.0
        • a2a
        • agent
        • agent-os
        • agent-sandbox
        • agentic

        githubmeasured growthOpen source ↗

        877GitHub stars+5 (+0.57 %)
      • 11

        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+2 (+2.0 %)
      • 12

        MCP
        Active

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

        TypeScriptLicense: MIT
        • ai-agents
        • claude
        • claude-ai
        • claude-code
        • claude-code-plugin

        githubmeasured growthOpen source ↗

        102GitHub stars+2 (+2.0 %)
      • 13

        MCP
        Active

        The Private Agent OS — search files, run AI agents, connect to 10,000+ tools via the complete protocol stack (MCP, AG-UI, A2UI, A2A). Zero cloud. Zero telemetry. On-device inference.

        Rust
        • a2a
        • a2ui
        • ag-ui
        • agent-orchestration
        • agent-os

        githubmeasured growthOpen source ↗

        30GitHub stars+1 (+3.4 %)
      • 14

        Skill
        Active

        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…

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

        githubmeasured growthOpen source ↗

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

        123GitHub stars+2 (+1.7 %)
      • 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+5 (+0.11 %)
      • 16

        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 735GitHub stars+5 (+0.09 %)
      • 17

        MCP
        Active

        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…

        PythonLicense: MIT
        • bigquery
        • claude-code
        • claude-code-plugin
        • faiss
        • mcp-server

        githubmeasured growthOpen source ↗

        177GitHub stars+2 (+1.1 %)
      • 18

        Skill
        Active

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

        PythonLicense: MIT
        • agent-memory
        • agent-skills
        • agentic-ai
        • agentic-rag
        • ai-agents

        githubmeasured growthOpen source ↗

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

        48GitHub stars+1 (+2.1 %)
      • 19

        MCP
        Active

        A semantic search engine for files and code.

        PythonLicense: MIT

          mcpmeasured growthOpen source ↗

          Install claude mcp add vexor -- uvx vexor

          239GitHub stars+2 (+0.84 %)
        • 20

          Agent
          Active

          TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.

          GoLicense: Apache-2.0
          • agent
          • agent-context
          • agent-memory
          • agentic
          • ai

          githubmeasured growthOpen source ↗

          40 479GitHub stars+4 (+0.010 %)
        • 21

          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 stars+1 (+1.5 %)
        • 22

          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 ↗

          71GitHub stars+1 (+1.4 %)
        • 23

          MCP
          Active

          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.

          JavaLicense: Apache-2.0
          • a2a
          • ai-agents
          • ai-orchestration
          • chatbot
          • conversation-memory

          githubmeasured growthOpen source ↗

          372GitHub stars+2 (+0.54 %)

        Learning resources

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

        1. 1

          agent-systems-handbook

          Agent
          ActiveOpen source ↗

          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
          githubResourcemeasured growth
          316GitHub stars+3 (+0.96 %)
        2. 2

          dspy-skills

          Skill
          ActiveOpen source ↗

          Collection of Claude Skills for DSPy framework - program language models, optimize prompts, and build RAG pipelines systematically

          PythonLicense: MIT
          • agent-skills
          • claude-code
          • claude-skills
          • dspy
          • llm
          github

          Install git clone https://github.com/OmidZamani/dspy-skills ~/.claude/skills/dspy-skills

          Resourcemeasured growth
          122GitHub stars+2 (+1.7 %)