Ross ROSS = Recommend OSS · open-source software intelligence for agents

Mintplex-Labs/anything-llm

Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience observed · 2026-08-28

github.com/Mintplex-Labs/anything-llm · homepage · JavaScript · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

95/100

  • Activity 99
  • Release rhythm 97
  • Longevity 84
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 20.5
  • age_days: 1187
  • days_rel: 20
  • days_push: 7
  • n_releases_24m: 29

Full methodology

Adoption not part of the score

65257 stars · 7192 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

AnythingLLM is an all-in-one, local-first AI application for chatting with your documents, running AI agents, and building workflows entirely on your own device or self-hosted server. It supports multiple LLM providers (Ollama, LM Studio, OpenAI, Anthropic, etc.), vector databases, multi-user access, and a developer API, with desktop, Docker, and cloud deployment options.

Use cases

  • chat with my pdf documents locally
  • run a private AI assistant without cloud API keys
  • build a RAG knowledge base from my files
  • self-host a multi-user AI chat for my team
  • run AI agents that use my local documents
  • transcribe and summarize meetings on-device
  • deploy a private ChatGPT alternative on Docker
  • connect Ollama or LM Studio to a nice chat UI

When to choose

  • you want a private, local-first AI assistant with no data leaving your machine
  • you need document Q&A (RAG) with a polished UI out of the box
  • you want multi-user workspaces and self-hosting via Docker
  • you want agent capabilities, web scraping, and custom tools without writing code

When to avoid

  • you need a lightweight library or SDK to embed RAG into your own codebase
  • you require fine-grained programmatic control over the RAG pipeline internals
  • you only need a raw LLM inference server rather than a full application

Facets

application · maturity active

rag chatbot agent-framework llm-inference vector-database chat-interface web-scraping speech-recognition self-hosted artificial-intelligence large-language-models chatbots self-hosted privacy developer-tools windows self-hosted cross-platform local-ai on-device-ai multi-user no-code-agents document-chat ollama lm-studio mit-license retrieval-augmented-generation ai-agents macos linux docker desktop web-server

10 sources

Member repositories

RepositoryRoleHealth v2
Mintplex-Labs/anything-llmmain95

For agents

markdown · JSON · MCP: product_card(name="Mintplex-Labs/anything-llm")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem