onyx-dot-app/onyx

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

What it solves

Onyx acts as a central knowledge layer that connects to your team's various applications, allowing AI agents to access and understand internal company data. It solves the problem of fragmented information by indexing data from over 50 sources, ensuring that AI tools have access to accurate, relevant, and secure internal context without needing to search through dozens of separate systems.

How it works

Onyx ingests data from your connected applications, maintaining metadata and permissions to create a reliable, low-latency index. When you ask a question, it filters this index to find the most relevant ground truth documents. This approach is more efficient than standard agentic searching, as it avoids the token-heavy process of iteratively querying multiple external sources. It can be deployed in self-hosted, air-gapped environments to ensure data sovereignty.

Who it’s for

Onyx is designed for teams and organizations of all sizes—from individuals to large enterprises—that need to integrate AI agents with their private company data while maintaining strict security, access controls, and data privacy.

Highlights

  • Agentic RAG: Combines a hybrid index with a custom agent harness for high-quality search and retrieval.
  • Deep Research: Supports multi-step research flows to generate in-depth reports.
  • Broad Connectivity: Integrates with 50+ applications and supports live web search via multiple providers.
  • Secure Execution: Includes a sandbox for running code and handling intermediate artifacts.
  • Flexible Deployment: Offers standard and lightweight modes, with support for Docker, Kubernetes, and cloud environments.
  • Enterprise-Ready: Features SSO, Role-Based Access Control (RBAC), audit logs, and analytics for secure organizational use.

Related

  • Project
    onyx-dot-app/onyx-foss

    Onyx is a self-hosted knowledge and context layer that connects to over 50 applications to provide AI agents with secure, relevant access to your organization's internal data.

  • Project
    xerrors/Yuxi

    Yuxi is an open‑source, Docker‑based platform for building private, multi‑tenant AI agents. It combines document ingestion, vector/RAG search, Neo4j knowledge‑graph construction, LangGraph‑driven multi‑agent orchestration, sandboxed file tools and fine‑grained team permissions, letting enterprises run custom agents on‑premise with their own LLM API keys.

  • Project
    odysseus-dev/odysseus

    Odysseus is a self‑hosted web app that combines chat, autonomous agents, research, document editing, email, notes, tasks and calendar into one AI‑powered workspace. It runs via Docker Compose, supports local or API language models, and is released under AGPL‑3.0.

  • Project
    ogx-ai/ogx

    OGX is an open‑source, model‑agnostic API server that mimics OpenAI’s REST endpoints. It lets you run any LLM (Llama, GPT, Gemini, etc.) locally or in the cloud, while keeping the same client code. In addition to standard chat/completion/embedding calls, OGX offers a “Responses” API for tool‑calling and RAG, versioned skill bundles, and native routes for Anthropic and Google GenAI SDKs. Install with a one‑line script, start the server, and point any OpenAI‑compatible client at it.

  • Dispatch
    OtoDock 1.6.0 – Self‑hosted AI Agent Platform for Company‑wide Automation

    OtoDock 1.6.0 is a self‑hosted, multi‑tenant platform that lets companies create, share and run Claude Code or Codex agents across departments, with built‑in security, scheduling, phone integration and a rich UI.