All Repos HereSaved (0)

Open-source repos for RAG and search

39 repos tagged RAG and search, sorted by GitHub stars. Add filters from the other category types to narrow the list.

39repos tagged RAG and search
Instead of ChatGPT PlusKit: Local LLMs, 20 compared
39 repos
Sort
Data from GitHub, checked

  1. firecrawl/firecrawl

    API that turns websites into clean Markdown or structured data for LLMs, with crawl and search.

    Web scraping, Web, Marketing, Engineering

    198k starsAGPL-3.0Updated 3 Nov 2026

  2. microsoft/markitdown

    Python tool that converts Office documents, PDFs and other files into Markdown for LLMs.

    LLM apps, Engineering

    194k starsMITUpdated 28 Oct 2026

  3. langgenius/dify

    Platform for building LLM apps, chatbots and agent workflows with a visual editor and knowledge base.

    LLM apps, AI agents, Chatbots, Docker, OpenAI, Operations, Engineering, SaaS, Agencies, No-code

    160k starsOtherUpdated 3 Nov 2026

  4. open-webui/open-webui

    Self-hosted chat UI for Ollama and OpenAI-compatible models with RAG, tools and user management.

    LLM apps, Chatbots, Ollama, OpenAI, Operations, IT and security, Self hosters

    158k starsOtherUpdated 3 Nov 2026

  5. langflow-ai/langflow

    Visual builder for agent and RAG flows that exports to APIs and MCP servers, with Python components.

    LLM apps, AI agents, Docker, Engineering, No-code

    156k starsMITUpdated 3 Nov 2026

  6. langchain-ai/langchain

    Framework for chaining LLM calls, tools and retrievers into applications across many model providers.

    LLM apps, AI agents, OpenAI, Anthropic, Engineering, SaaS

    149k starsMITUpdated 3 Nov 2026

  7. Shubhamsaboo/awesome-llm-apps

    Runnable collection of LLM app and agent templates for RAG, voice, MCP and multi-agent teams.

    LLM apps, AI agents, OpenAI, Anthropic, Engineering, Indie hackers

    144k starsApache-2.0Updated 23 Oct 2026

  8. infiniflow/ragflow

    RAG engine with deep document parsing that answers questions from PDFs, tables and scans with citations.

    Knowledge base, Docker, Operations, Customer support, Legal, Finance and fintech

    93.4k starsApache-2.0Updated 3 Nov 2026

  9. unclecode/crawl4ai

    Open-source crawler that outputs LLM-ready Markdown and supports structured extraction.

    Web scraping, Web, Engineering, Data and analytics

    86.8k starsApache-2.0Updated 3 Nov 2026

  10. nomic-ai/gpt4all

    Desktop chat app for running open models on an ordinary laptop, with chat over your local documents.

    LLM apps, Operations, Engineering, Self hosters

    77.3k starsMITUpdated 28 May 2025

  11. docling-project/docling

    Converts PDFs, Office files and images into clean Markdown or JSON ready for RAG and AI pipelines.

    LLM apps, Engineering, Data and analytics

    70k starsMITUpdated 3 Nov 2026

  12. Mintplex-Labs/anything-llm

    Desktop and Docker app for chatting with your documents, with agents and a no-code agent builder.

    LLM apps, AI agents, Docker, Ollama, Operations, Self hosters

    67.9k starsMITUpdated 31 Oct 2026

  13. zylon-ai/private-gpt

    API layer for building private AI apps on local models, with document Q&A, tools and text-to-SQL.

    LLM apps, Ollama, OpenAI, Engineering, IT and security, Legal, Healthcare, Self hosters

    57.6k starsApache-2.0Updated 29 Oct 2026

  14. CherryHQ/cherry-studio

    Desktop workspace for chatting with many cloud and local models, with assistants, knowledge bases and MCP tools.

    LLM apps, Ollama, OpenAI, Operations

    53.2k starsAGPL-3.0Updated 3 Nov 2026

  15. run-llama/llama_index

    Python and TypeScript framework for connecting language models to your documents and building retrieval agents.

    AI agents, LLM apps, OpenAI, Engineering, SaaS

    52.8k starsMITUpdated 27 Oct 2026

  16. agno-agi/agno

    Python framework and runtime for building agents with memory, knowledge and tools, and serving them.

    AI agents, Engineering, SaaS

    43k starsApache-2.0Updated 3 Nov 2026

  17. lfnovo/open-notebook

    Self-hosted NotebookLM alternative that generates podcasts from your research sources.

    Repurposing, Voiceover, Docker, Marketing, Creators, Media and publishing, Podcasts, Self hosters

    41.4k starsMITUpdated 2 Nov 2026

  18. HKUDS/LightRAG

    Graph-based RAG library that builds a knowledge graph from documents for better retrieval.

    Engineering

    40.5k starsMITUpdated 29 Oct 2026

  19. searxng/searxng

    Private metasearch engine you host yourself that queries many search providers without profiling its users.

    Docker, Web, IT and security, Self hosters

    39.2k starsAGPL-3.0Updated 2 Nov 2026

  20. ItzCrazyKns/Vane

    Self-hosted AI answer engine that searches the web and cites sources, a Perplexity alternative.

    Docker, Ollama, Marketing, Data and analytics, Self hosters

    38k starsMITUpdated 1 Sept 2026

  21. khoj-ai/khoj

    Personal AI assistant that answers from your documents and the web and runs scheduled research.

    AI agents, Knowledge base, Ollama, Operations, Self hosters

    38k starsAGPL-3.0Updated 2 Aug 2026

  22. onyx-dot-app/onyx

    Workplace AI search and chat that connects to 40+ sources like Slack, Drive and Confluence.

    Knowledge base, Chatbots, Slack, Docker, Operations, Customer support, SaaS, Self hosters

    33.2k starsOtherUpdated 3 Nov 2026

  23. stanford-oval/storm

    LLM system that researches a topic on the web and writes a long, cited, Wikipedia-style article.

    Content writing, LLM apps, OpenAI, Marketing, Media and publishing, Education

    31.8k starsMITUpdated 30 Sept 2025

  24. assafelovic/gpt-researcher

    Agent that researches a topic across many web sources and writes a cited report.

    AI agents, Content writing, SEO research, OpenAI, Marketing, Data and analytics, Media and publishing, Agencies

    30.5k starsApache-2.0Updated 11 Oct 2026

  25. labring/FastGPT

    Knowledge-base Q&A platform with visual workflow orchestration for building support bots.

    LLM apps, Chatbots, Knowledge base, Docker, OpenAI, Customer support, Operations, SaaS, No-code, Self hosters

    30k starsOtherUpdated 3 Nov 2026

  26. mastra-ai/mastra

    TypeScript framework for AI agents, workflows, RAG and evals, aimed at web developers.

    AI agents, LLM apps, Vercel, Engineering, SaaS

    29.3k starsOtherUpdated 3 Nov 2026

  27. deepset-ai/haystack

    Framework for production RAG pipelines, search and agents with pluggable retrievers and models.

    LLM apps, AI agents, Engineering

    26.9k starsApache-2.0Updated 2 Nov 2026

  28. 1Panel-dev/MaxKB

    Enterprise knowledge-base assistant with RAG and agent workflows, embeddable into websites.

    Knowledge base, Chatbots, Docker, Ollama, Customer support, Operations, B2B services, SaaS, No-code, Self hosters

    23.1k starsGPL-3.0Updated 3 Nov 2026

  29. PromtEngineer/localGPT

    Ask questions about your own files using models that run on your machine, so documents never leave it.

    LLM apps, Ollama, Engineering, Legal, Self hosters

    22.2k starsMITUpdated 26 Aug 2026

  30. arc53/DocsGPT

    Self-hosted assistant that answers questions from your docs and help content, embeddable as a widget.

    Chatbots, Knowledge base, OpenAI, Ollama, Customer support, SaaS, Self hosters

    18.4k starsMITUpdated 2 Nov 2026

  31. MODSetter/SurfSense

    Self-hosted research assistant that searches your notes, Slack, Notion and the web, like NotebookLM.

    Knowledge base, Slack, Notion, Operations, Self hosters

    16.7k starsApache-2.0Updated 2 Nov 2026

  32. n8n-io/self-hosted-ai-starter-kit

    Docker Compose bundle of n8n, Ollama, Qdrant and Postgres for running local AI workflows.

    Workflow automation, AI agents, Docker, Ollama, Operations, Engineering, Self hosters

    15.3k starsApache-2.0Updated 12 Oct 2026

  33. jina-ai/reader

    Converts any URL into LLM-friendly text by prefixing it with a reader endpoint.

    Web scraping, Web, Engineering

    12.2k starsApache-2.0Updated 22 May 2026

  34. LearningCircuit/local-deep-research

    Local deep-research assistant that searches web and academic sources and writes cited reports.

    AI agents, Ollama, Docker, Data and analytics, Education, Self hosters

    9.5k starsMITUpdated 3 Nov 2026

  35. wassupjay/n8n-free-templates

    Set of free n8n templates combining AI models, vector stores and common business apps.

    Workflow automation, AI agents, OpenAI, Operations, Marketing, Agencies, No-code

    6.2k starsUpdated 1 Aug 2025

  36. okfn-brasil/querido-diario

    Scrapes and indexes Brazilian municipal official gazettes so the public can search them.

    Web scraping, Data and analytics, Government, Media and publishing, Data journalism

    1.4k starsMITUpdated 13 Oct 2026

  37. freelawproject/courtlistener

    Code behind CourtListener, a searchable archive of US court opinions, dockets and oral arguments.

    Web scraping, Web, Legal and compliance, Legal, Nonprofit, Data journalism

    1.1k starsOtherUpdated 3 Nov 2026

  38. lawglance/lawglance

    RAG legal assistant that answers law questions from curated jurisdiction knowledge bases.

    LLM apps, Chatbots, OpenAI, Legal and compliance, Legal

    334 starsApache-2.0Updated 22 Sept 2026

  39. harvard-lil/olaw

    Harvard LIL workbench for experimenting with retrieval-augmented legal AI over court data.

    LLM apps, OpenAI, Ollama, Legal and compliance, Legal, Education

    166 starsMITUpdated 30 Oct 2024