COR Brief
Join Beta
AI Tools›Conversational AI›Onyx
Conversational AI

Onyx

Onyx is an open-source AI platform that offers a self-hostable chat user interface integrating with any large language model (LLM) to support enterprise search and AI assistance. It connects to internal team knowledge sources, applications, and people, enabling features such as internal and web search as well as agent-based interactions. The platform supports retrieval-augmented generation (RAG) through hybrid search and knowledge graphs, and provides connectors to over 40 applications with real-time synchronization and access control enforcement. Onyx also includes developer APIs for messaging, agents, LLMs, actions, and user authentication, allowing integration into custom applications or products. Deployment options include airgapped environments for enhanced security.

Updated Dec 16, 2025freemium
Visit Onyx ↗Visual Guide
Overview

Onyx is an open-source, self-hostable AI platform that integrates with any LLM to provide enterprise search, AI assistance, and custom agent capabilities.

Pricing
Free under MIT license
Category
Conversational AI
Company
Visual Guide
Interactive PresentationOpen Fullscreen ↗
Key Features
01
Create agents with specific instructions, knowledge bases, and actions to automate workflows and interactions.
02
Supports hybrid search and knowledge graphs to enhance responses using files and documents.
03
Integrates with over 40 knowledge sources, syncing updates in real time while respecting fine-grained access controls.
04
Enables web search through Google PSE, Exa, Serper, an in-house scraper, or Firecrawl to supplement internal data.
05
Executes Python code, performs data analysis, and generates visualizations within isolated Docker containers (currently in alpha).
06
Provides APIs for messages, agents, LLMs, actions, and user authentication to facilitate integration into apps or products.
Real-World Use Cases

Enterprise Knowledge Search

Teams connect Onyx to internal documents, apps, and databases to enable natural language search and retrieval-augmented responses.

Custom AI Agents

Organizations build agents with tailored instructions and actions to automate internal workflows and assist employees.

Developer Integration

Developers use Onyx APIs to embed AI chat and search capabilities into their own applications or products.

Quick Start
1
Deploy Onyx Locally
Use the quickstart guide on the official website to self-host the Community Edition.
2
Try Onyx Cloud
Sign up for the 14-day free trial of Onyx Cloud without needing a credit card.
3
Configure LLMs and Knowledge Sources
Connect your preferred LLMs and integrate knowledge sources and apps via the Onyx interface.
4
Set Up Custom Agents
Create and configure agents with instructions, knowledge, and actions to suit your workflows.
5
Generate API Keys
Create API keys for integration and test features such as chat and search functionality.
6
Review Documentation
Consult the official documentation for detailed information on core features and administrative options.
📊

Strategic Context for Onyx

Get weekly analysis on market dynamics, competitive positioning, and implementation ROI frameworks with AI Intelligence briefings.

Try Intelligence Free →
7 days free · No credit card
Pricing
Model: freemium
Community Edition (CE)
Free under MIT license
  • Self-hostable open-source platform
  • Supports any LLM
  • Connectors to 40+ apps
  • APIs for integration
Enterprise Edition (EE)
Not publicly disclosed
  • Additional features for larger organizations

A 14-day free trial of Onyx Cloud is available without requiring a credit card.

Assessment
Strengths
  • Supports any LLM including self-hosted options like Ollama or vLLM
  • Open source under MIT license enabling self-hosting and customization
  • Connectors to over 40 applications with real-time synchronization and fine-grained access controls
  • Developer APIs covering messaging, agents, LLMs, actions, and user authentication
  • Active community including developers at top companies
Limitations
  • Enterprise Edition features require paid access beyond the free Community Edition
  • Code interpreter feature is currently in alpha stage
  • Specific pricing details for Enterprise Edition are not publicly available