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

onyx

Onyx is an open source AI platform that serves as the application layer for large language models, providing a feature-rich interface that can be self-hosted by anyone. It enables advanced AI capabilities like RAG, web search, code execution, and deep research while supporting all major LLM providers.

Key Features

• Agentic RAG: Hybrid search with AI agents for superior information retrieval and answer quality
• Deep Research: Multi-step research flows for generating in-depth reports and analysis
• Custom Agents: Build AI agents with unique instructions, knowledge, and configurable actions
• Web Search: Browse the internet with support for multiple search providers and web crawling
• Code Execution: Run code in sandboxes to analyze data, create visualizations, and modify files
• Voice & Artifacts: Text-to-speech and speech-to-text chat plus document and graphic generation
• Enterprise Features: SSO, RBAC, analytics, audit trails, and whitelabeling for organizations

Use Cases

• Enterprise Knowledge Management: Connect 50+ data sources via indexing connectors for organization-wide information retrieval
• Research & Analysis: Generate comprehensive research reports and deep dives with multi-step AI workflows
• Team Collaboration: Share chats and custom agents across teams with role-based access controls
• Custom Automation: Build specialized AI agents with unique instructions and integrate external applications via MCP
• Information-Heavy Applications: Deploy RAG systems with hybrid indexing for semantic and keyword search

Who Is It For

Onyx is designed for individuals, teams, and enterprises seeking a self-hosted AI chat platform. It serves researchers, knowledge workers, organizations requiring data privacy and control, and teams building custom AI agents.