# onyx-dot-app/onyx

Open Source AI Platform - AI Chat with advanced features that works with every LLM

Repository: https://github.com/onyx-dot-app/onyx
Canonical: https://ross.abutalabs.com/products/onyx
Homepage: https://onyx.app
Language: Python
License: NOASSERTION
License Family: other
Topics: enterprise-search, rag, ai-chat, chatgpt, gen-ai, nextjs, python, information-retrieval, ai, llm, llm-ui, chatui, self-hosted, vector-search
Last push: 2026-08-27T00:25:49+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 87
- inputs: {"age_days": 1224, "days_push": 7, "days_rel": 8, "gap_med": 0.0, "n_releases_24m": 229}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 31777, forks 4378 (observed 2026-08-28T04:11:57.139214+00:00)

## What it is
Onyx is an open-source, self-hostable AI chat platform that connects LLMs to company documents, apps, and people via RAG, 50+ data connectors, and MCP-based actions. It provides a feature-rich chat UI with agentic search, deep research, custom agents, web search, and code execution.

## Use cases
- chat with my company documents using an llm
- self-hosted enterprise ai search assistant
- build custom ai agents connected to internal knowledge
- run deep research reports over internal and web sources
- index slack, google drive, and confluence for rag
- open-source chatgpt alternative for teams
- connect llm agents to external tools via mcp

## When to choose
- you want a self-hosted, feature-rich AI chat grounded in your organization's knowledge
- you need many out-of-the-box connectors to index company apps and documents
- you want agentic RAG, deep research, and MCP actions in one deployable platform
- you need RBAC, SSO, and on-premise deployment options

## When to avoid
- you only need a lightweight library to embed RAG into your own app
- you want a fully managed SaaS without self-hosting overhead
- you need a minimal chat UI without search or connector infrastructure

## Facets
- artifact type: application
- maturity: active
- function: rag, chatbot, search-engine, agent-framework, chat-interface, mcp, web-scraping, llm-inference
- domain: artificial-intelligence, large-language-models, erp, self-hosted
- platform: self-hosted, python, cross-platform
- tags: enterprise-search, ai-chat, deep-research, connectors, vector-search, nextjs, code-interpreter, slack-integration, retrieval-augmented-generation, search, ai-agents, docker, web-server

## Member repositories
- onyx-dot-app/onyx (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:57.139214+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:52:14.497759+00:00, confidence not recorded.
  - readme: https://github.com/onyx-dot-app/onyx (fetched 2026-08-28T04:11:57.139214+00:00, sha ec0c5e9a1b5f)
  - homepage: https://onyx.app (fetched 2026-08-29T07:49:11.578004+00:00, sha 6304c8f21387)
  - site_page: https://onyx.app/pricing (fetched 2026-08-29T07:49:11.580669+00:00, sha 0b37cbba5f93)
- Data as of 2026-08-30T08:39:29.467469+00:00.