Logo
Deploy Now

SaaS Alternative

Perplexity Glean

Categories

Self-Hosted Developer Tools Collaboration LLM Knowledge Management RAG AI Assistant Enterprise Search

Stars

31,704

Forks

4,368

Watchers

156

Developer links

Last Updated: 08-21-2026 09:02 PM (UTC)

Onyx

Formerly known as Danswer and now backed by over 31,000 GitHub stars with 253 releases, Onyx delivers a production-ready AI platform that turns any LLM into a context-aware enterprise assistant connected to your organization's actual knowledge. The agentic RAG pipeline combines BM-25 keyword search with prefix-aware embedding models in a hybrid index, then deploys AI agents to retrieve, verify, and synthesize answers with source citations from over 40 connected workplace tools including Google Drive, Confluence, Slack, Notion, Jira, SharePoint, GitHub, and Linear. Custom AI assistants with configurable prompts, backing knowledge sets, and document-level access control enable specialized agents for engineering, sales, support, and research workflows. The platform supports every major LLM provider — Anthropic Claude, OpenAI, Google Gemini, plus self-hosted options via Ollama, LiteLLM, and vLLM for fully air-gapped deployments. Beyond chat, Onyx provides web search with Serper, Google PSE, Brave, and SearXNG integration, an in-house web crawler, code execution, file creation, and multi-step deep research with report generation. Enterprise features include SSO via Google OAuth, OIDC, or SAML with SCIM provisioning, role-based access control, usage analytics by team and agent, query history auditing, PII removal through custom code hooks, and full whitelabeling. Deploy via Docker Compose on any infrastructure. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed (Community Edition).

Onyx
Onyx
Onyx

Benefits

  • 40+ Workplace Tool Connectors
  • Indexes Google Drive, Confluence, Slack, Notion, Jira, SharePoint, GitHub, Linear, and dozens more with automatic sync, document-level access control, and real-time content updates.
  • Best-in-Class Hybrid Search
  • Combines BM-25 keyword matching with prefix-aware embedding models and AI agents for information retrieval, delivering cited answers with source document links and confidence scores.
  • Any LLM, Fully Air-Gapped
  • Supports Anthropic, OpenAI, Gemini, and self-hosted models via Ollama, LiteLLM, or vLLM, enabling completely air-gapped deployments where no data leaves your infrastructure.
  • Enterprise-Ready Access Control
  • SSO via Google OAuth, OIDC, or SAML with SCIM user provisioning, role-based access control, query history auditing, usage analytics, and custom PII-removal code hooks.

Features

  • Agentic RAG Pipeline
  • AI agents decompose queries, retrieve from hybrid indexes, verify facts across sources, and synthesize cited answers with multi-hop reasoning and source attribution.
  • Custom AI Assistants
  • Create specialized assistants with configurable system prompts, backing knowledge sets, document access scoping, and per-assistant LLM selection for different team workflows.
  • Deep Research Mode
  • Multi-step research agent browses the web, reads documents, executes code, and generates structured reports with citations from both internal knowledge and external sources.
  • Web Search Integration
  • Browses the internet via Serper, Google PSE, Brave, SearXNG, or the built-in crawler to augment internal knowledge with current external information.
  • Slack Bot Integration
  • Deploys directly into Slack channels to answer questions, search across all connected sources, and deliver AI-powered responses where teams already collaborate.