Home › Agent Applications › Onyx

Onyx - AI Agent Applications Tool

Overview

Onyx is an open-source, self-hostable chat UI and agent platform designed for teams building conversational products and research workflows. According to the project description, Onyx provides Retrieval-Augmented Generation (RAG), a deep research mode for multi-document synthesis, MCP agent orchestration, built-in web search, and more than 40 connectors to external data sources. The project ships as a Community Edition under an MIT-compatible license and also offers an Enterprise edition for commercial deployments. Onyx targets users who need a production-ready chat UI with extensible integration points: you can connect knowledge stores and third-party services through the available connectors, run RAG pipelines for context-aware responses, and orchestrate agents for multi-step tasks. The repository shows active development and a sizeable community (see GitHub stats), positioning Onyx as a practical choice for teams wanting an auditable, self-hosted alternative to hosted chat UIs. Enterprise features and commercial support are provided separately by the maintainers; specifics about Enterprise pricing are not published in the public repository.

GitHub Statistics

  • Stars: 17,007
  • Forks: 2,275
  • Contributors: 168
  • License: NOASSERTION
  • Primary Language: Python
  • Last Updated: 2026-01-09T20:04:22Z
  • Latest Release: v2.7.1

According to the GitHub repository, Onyx has 17,007 stars, 2,275 forks, and 168 contributors, indicating strong community interest and contributor activity. The repository's last commit was on 2026-01-09, showing recent maintenance. The project license field on GitHub is listed as NOASSERTION, while project messaging references a Community (MIT) edition and a separate Enterprise edition. Active issue and PR traffic plus dozens of contributors suggest healthy community engagement and ongoing feature development.

Installation

Install via docker:

git clone https://github.com/onyx-dot-app/onyx.git
cd onyx
docker compose up -d

Key Features

  • Retrieval-Augmented Generation (RAG) pipelines for context-aware responses
  • Deep research mode to synthesize findings across multiple documents
  • MCP agent orchestration for multi-step automated workflows
  • Built-in web search integration for live information retrieval
  • 40+ connectors to external data sources and services
  • Self-hostable architecture for on-premises or VPC deployments
  • Community Edition (MIT) with an Enterprise edition available

Community

Onyx has an active GitHub community with 17k stars, 2.2k forks, and 168 contributors. Frequent commits and open issues indicate ongoing development; Enterprise support is available for commercial users.

Last Refreshed: 2026-01-09

Key Information

  • Category: Agent Applications
  • Type: AI Agent Applications Tool
Visit Official Website

Related Tools

leon-ai/leon

An open-source personal assistant that runs on your own server, providing a customizable, self-hosted AI assistant experience.
DeepSeek-R1

An autonomous agent designed for deep local and web research, capable of generating detailed reports with citations for various topics.
Nanobrowser

Open-source browser extension providing multi-agent, on-device web automation and navigation with configurable LLMs per agent.
Second Me

Second Me is an open‐source platform that lets you train and deploy a personalized AI self. It uses hierarchical memory modeling and the Me-Alignment Algorithm to capture your memories and identity, enabling your AI to switch roles, collaborate on a decentralized network, and serve as a private, self-hosted personal assistant.
Manus AI

Manus AI is an autonomous AI agent designed to execute complex tasks across multiple domains, including report writing, data analysis, content generation, and more. It features multi-modal capabilities, advanced tool integration (e.g., web browsers, code editors, database systems), and adaptive learning to optimize performance. The tool claims state-of-the-art performance on the GAIA benchmark, positioning itself as a competitive alternative to leading AI models.
Agentic Browser

An open-source AI agent designed for web automation and scraping. It orchestrates specialized agents (Planner, Browser, and Critique) to automate browser interactions such as form filling, data extraction, e-commerce searches, and content retrieval via a natural language interface.