OSS Tanbou
View on GitHubProject website

turn internal knowledge into a context layer for AI agents

OSS scale score Not calculatedOSS health 100
About these scores

OSS scale score is an unbounded metric that log-compresses and weights Stars, Watchers, Forks, and Contributors. Discovery score is the current OSS scale score minus the score at discovery. Update pace is commits in the last 30 days, growth momentum is the OSS scale score difference within the recent observation window, and OSS health is a 0–100 rating based on available recency, Community Health, and release data.

Stars
32,294
Primary language
Python
License
Not determined
Repository last updated
Sep 30, 2026
On this page

Overview

Onyx ingests documents, metadata, and permissions from multiple applications and uses hybrid search and RAG to ground AI chat, custom agents, deep research, and MCP clients. It supports self-hosted and air-gapped deployments.

Features and best fit

Based on official documentation; not hands-on tested · Content checked:

Key features

Index knowledge and permissions from more than 50 connectors

Documents and metadata from internal applications are ingested into search and RAG indexes while retaining access-control context.

Sources: [2]

Serve the same context to search, agents, and MCP clients

Hybrid search, deep research, custom agents, external actions, and the MCP server can share one knowledge representation.

Sources: [2]

Best fit

Fits organizations connecting enterprise knowledge to AI on controlled infrastructure

Databases, indexes, and processing can remain self-hosted, with local LLM and embedding options for stronger data-sovereignty requirements.

Sources: [2][6]

Before adoption

Standard and Lite deployments have different resource and feature profiles

Standard mode includes vector and keyword indexes, workers, model services, Redis, and MinIO, while Lite targets a sub-1GB chat UI and cannot index documents.

Sources: [2]

Separate Community core licensing from Enterprise code

The root LICENSE applies MIT outside ee directories, while enterprise directories require an Enterprise License for production use. Check the paths and features being deployed.

Sources: [3][4]

Official sources

  1. [1]onyx-dot-app/onyx repository(2026-09-30)
  2. [2]Onyx README(2026-09-30)
  3. [3]Onyx repository license(2026-09-30)
  4. [4]Onyx Enterprise License(2026-09-30)
  5. [5]Onyx v4.8.2 release(2026-09-30)
  6. [6]Onyx Docker Compose deployment guide(2026-09-30)
Supplemental curator note

Onyx indexes knowledge and permissions from more than 50 applications such as Slack, Drive, and GitHub and exposes that context to AI search, RAG, agents, and MCP clients. Community Edition core code is MIT-licensed, while backend/ee and web ee directories use the Onyx Enterprise License and require a valid Enterprise License for production use. The repository should not be treated as uniformly MIT-licensed.

Try it in 3 steps

  1. 1

    Clone Onyx v4.8.2

    Check out the release-pinned Docker Compose deployment files.

    git clone --depth 1 --branch v4.8.2 https://github.com/onyx-dot-app/onyx.git && cd onyx/deployment/docker_compose
  2. 2

    Create a local evaluation environment

    Pin the release images and generate the required authentication secret. Review every default credential, including MinIO settings, before production use.

    cp env.template .env && printf "\nIMAGE_TAG=v4.8.2\nUSER_AUTH_SECRET=%s\n" "$(openssl rand -hex 32)" >> .env
  3. 3

    Start with the development overlay

    Run the stack for local evaluation. Use docker-compose.prod.yml and the security checklist for production.

    docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d --wait
Check the official README

Growth

Growth trends · Last 30 days

32,294 Stars

Trend data is still being collected.

Built with

Categories and tags

Categories

Tags

GitHub data

GitHub dataView detailed GitHub data
View on GitHub

GitHub Topics

  • ai
  • ai-chat
  • chatgpt
  • chatui
  • enterprise-search
  • gen-ai
  • information-retrieval
  • llm
  • llm-ui
  • nextjs
  • python
  • rag
Stars
32,294
Forks
4,516
Watchers
159
Open issues
508
Owner type
Organization
Primary language
Python
License
Not determined
Repository last updated
Sep 30, 2026
Write a related article

Share a guide or use case for this OSS in Markdown. Articles are published after administrator approval.

Report incorrect information

Tell us if any listing information is incorrect or outdated.

After reading this page, do you know what to do next?