Onyx provides open-source AI chat that can work with different language models.

github.com/onyx-dot-app/onyx
Onyx homepage screenshot

About Onyx

Onyx is a knowledge and context layer for teams and AI agents. It connects to 50+ applications to index data with metadata and permissions, making it available for chat, search and research. It works with self-hosted and proprietary language models and embedding models, which can also run locally. It supports custom agents, web search, external actions through MCP, code execution in a sandbox, generated artifacts, voice interaction, and access from web, desktop, Slack and Discord with shared permissions. Self-hosted deployment keeps the document index, database and processing in self-contained services, while use of external LLM providers, search services and connected apps involves external processing.

Key features

  • Indexes knowledge from 50+ connected applications with metadata and permissions
  • AI chat compatible with self-hosted and proprietary LLM providers
  • Build custom agents with selected knowledge subsets and instructions
  • Augment answers with live web search and web crawler
  • Execute code and handle artifacts in secure sandbox
  • Take actions in external applications via MCP integrations
Best for: Teams that want AI chat and agents over internal application knowledge with self-hosted processing.
Good for
  • Self-hosted deployment where index, database and processing stay in self-contained services
  • Works with self-hosted and proprietary LLM and embedding models, including local operation
  • Applies source permissions across web, desktop, Slack and Discord access

Onyx at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Not stated
Language
English
Last checked
Oct 5, 2026 · Online when checked
Listed
Oct 5, 2026

Onyx alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Chatbots & Assistants

Well-known listings from the same topic.

All 238

Onyx FAQ

How does Onyx work?
It pulls data with metadata and permissions from connected sources and ingests it into an internal representation for search and other downstream uses.
Which language models does it support?
All major providers, including self-hosted options like Ollama, LiteLLM and vLLM, and proprietary options like Anthropic, OpenAI and Gemini.
How is organizational data handled?
It offers air-gappable self-hosted deployment where the index, database and processing run in self-contained services, with a choice of embedding model and LLM provider.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing