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

88

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
    活跃

    Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.

    mcp实测增长打开来源 ↗

    安装 claude mcp add rag-mcp -- uvx jaimenbell-rag-mcp

    0GitHub 星标稳定
  2. 2
    已放弃

    MCP server for YandexGPT — completions, embeddings, classification, summarization (Russia)

    mcp实测增长打开来源 ↗

    安装 claude mcp add yandexgpt-mcp -- npx @theyahia/yandexgpt-mcp

    0GitHub 星标稳定
  3. 3

    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.

    github实测增长打开来源 ↗

    64 675GitHub 星标+396 (+0.62 %)
  4. 4

    其他
    活跃

    The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

    github实测增长打开来源 ↗

    108 815GitHub 星标+271 (+0.25 %)
  5. 5

    其他
    活跃

    An intentionally vulnerable OWASP LLM Top 10 training platform for AI Security, Prompt Injection, RAG Security, Agent Security, and GenAI penetration testing.

    github实测增长打开来源 ↗

    311GitHub 星标+6 (+2.0 %)
  6. 6

    其他
    活跃

    Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI…

    github实测增长打开来源 ↗

    24 797GitHub 星标+146 (+0.59 %)
  7. 7

    活跃

    Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you…

    github实测增长打开来源 ↗

    39 491GitHub 星标+53 (+0.13 %)
  8. 8

    其他
    活跃

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

    github实测增长打开来源 ↗

    154 387GitHub 星标+601 (+0.39 %)
  9. 9

    其他
    活跃

    Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

    github实测增长打开来源 ↗

    34 377GitHub 星标+127 (+0.37 %)
  10. 10

    智能体
    活跃

    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.

    github实测增长打开来源 ↗

    40 487GitHub 星标+9 (+0.02 %)
  11. 11

    其他
    活跃

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

    github实测增长打开来源 ↗

    9 434GitHub 星标+10 (+0.11 %)
  12. 12

    其他
    活跃

    Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

    github实测增长打开来源 ↗

    45 962GitHub 星标+106 (+0.23 %)
  13. 13

    其他
    活跃

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for…

    github实测增长打开来源 ↗

    26 408GitHub 星标+56 (+0.21 %)
  14. 14

    其他
    活跃

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

    github实测增长打开来源 ↗

    5 741GitHub 星标+10 (+0.17 %)
  15. 15

    智能体
    活跃

    Incremental engine for long horizon agents 🌟 Star if you like it!

    github实测增长打开来源 ↗

    11 459GitHub 星标+29 (+0.25 %)
  16. 16

    其他
    活跃

    Graph-Native Infrastructure for Context and Accountable AI Systems

    github实测增长打开来源 ↗

    11 884GitHub 星标+735 (+6.6 %)
  17. 17

    活跃

    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.

    github实测增长打开来源 ↗

    3 249GitHub 星标+2 (+0.06 %)
  18. 18

    应用
    活跃

    World's first open-source enterprise world model.

    github实测增长打开来源 ↗

    3 799GitHub 星标+2 967 (+356.6 %)
  19. 19

    其他
    活跃

    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.

    github实测增长打开来源 ↗

    4 432GitHub 星标+3 (+0.07 %)
  20. 20

    应用
    活跃

    User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

    github实测增长打开来源 ↗

    150 860GitHub 星标+599 (+0.40 %)
  21. 21

    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.

    github实测增长打开来源 ↗

    68 835GitHub 星标+901 (+1.3 %)
  22. 22

    智能体
    活跃

    The agent engineering platform.

    github实测增长打开来源 ↗

    145 605GitHub 星标+391 (+0.27 %)
  23. 23

    智能体
    活跃

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

    github实测增长打开来源 ↗

    3 652GitHub 星标+1 125 (+44.5 %)
  24. 24

    智能体
    活跃

    FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, letting you easily develop and deploy complex…

    github实测增长打开来源 ↗

    29 561GitHub 星标+67 (+0.23 %)

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
    活跃打开来源 ↗

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

    github

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

    资源实测增长
    135 960GitHub 星标+648 (+0.48 %)