Logo
Deploy Now

SaaS Alternative

ChatGPT Plus Notion AI Glean Danswer

Categories

Productivity AI LLM Knowledge Base Chatbot RAG Document Management Search

Stars

62662

Forks

6849

Watchers

399

Developer links

Last Updated: 07-06-2026 10:47 AM (UTC)

AnythingLLM

Chat with your own documents: AnythingLLM, from Mintplex Labs, wraps retrieval-augmented generation (RAG) in an open-source application anyone can run. You organize content into workspaces, each an isolated namespace with its own documents, vector embeddings, chat history, and settings, so one instance can hold several separate knowledge bases. Upload PDFs, DOCX, TXT, and other formats, or scrape web pages; the built-in collector parses and chunks them into a vector database (LanceDB by default, with Pinecone, Chroma, Qdrant, and others supported). Answers cite their source documents. It works with both cloud LLMs (OpenAI, Anthropic, Gemini) and local ones via Ollama or LM Studio, and the embedding model is separately configurable. Beyond RAG chat, it includes AI agents that can browse the web and run tools, an embeddable chat widget for your website, a developer API, and multi-user mode with admin, manager, and default roles plus per-workspace access control. Context assembly is smarter than naive RAG: pinned documents, attached files, vector search hits, and recent chat history are combined under a token budget so the model's context window is filled efficiently, and each workspace supports multiple independent conversation threads against the same knowledge base. Because the embedding model, vector store, and chat LLM are all independently swappable, you can move between providers without re-ingesting a single document. The stack is Node.js with a React frontend, MIT-licensed.

AnythingLLM

Benefits

  • Private Document Q&A
  • Documents are parsed, embedded, and queried entirely on your instance. Sensitive contracts, internal docs, and research never pass through a third-party chat product's retention pipeline.
  • Answers You Can Verify
  • Every response cites the source documents and chunks it drew from, so users can check claims against the original text instead of trusting the model blindly.
  • Workspace Isolation
  • Each workspace is a separate namespace for documents, embeddings, and chat history. Legal, engineering, and support teams can run distinct knowledge bases on one instance without cross-contamination.
  • Provider Flexibility
  • Swap between cloud LLMs and local models served by Ollama without re-ingesting documents. Embedding model and vector database are independently configurable.

Features

  • Multi-Format Document Ingestion
  • PDF, DOCX, TXT, CSV, and more are parsed by a dedicated collector service, chunked, embedded, and stored in the workspace's vector namespace. Web scraping pulls in page content.
  • RAG with Context Assembly
  • Context is assembled from pinned documents, attached files, vector search results, and recent chat history, with token-budget management to fill the model's context window efficiently.
  • Conversation Threads
  • Multiple independent threads per workspace keep separate lines of inquiry against the same knowledge base without history overlap.
  • AI Agents
  • Workspace agents can browse the web, summarize documents, and invoke tools during a conversation, extending chat beyond retrieval.
  • Multi-User Mode and Permissions
  • Instance-level users with admin, manager, and default roles, plus per-workspace access control, available in the server deployment.
  • Embeddable Widget and API
  • Drop a chat widget scoped to a workspace onto any website, or integrate programmatically through the developer API.