Self-hosted alternatives to Onyx

2 projects· by score

Also in LLM Integration

Not listed as Onyx alternatives, but they cover the same ground and are worth a look.

mcp-searxngOpen-source MCP server that adds privacy-focused web search and URL reading to AI clients like Claude and Cursor through a self-hosted SearXNG instance.
ManifestSelf-hosted, open-source LLM gateway: one OpenAI-compatible endpoint routes agents to 300+ models with provider fallbacks, cost tracking and full request logs.
oss-llmops-stackAn open-source, self-hosted LLMOps platform pairing LiteLLM's unified model gateway with Langfuse's tracing, evaluation, and prompt tooling for production AI workloads.
DesktopCommanderMCPOpen-source, self-hosted MCP server that gives Claude, ChatGPT and other AI clients terminal, file and process control on your own machine.
9RouterOpen-source, self-hosted AI router giving coding CLIs one OpenAI-compatible endpoint, 3-tier fallback across 60+ providers, token compression and a local dashboard.
Weave RouterOpen-source LLM model router for coding agents like Claude Code, Codex, and Cursor; self-hosted with Docker Compose, it picks the cheapest capable model per request.

All 84 LLM Integration projects

2 open-source, self-hosted alternatives to Onyx are listed here, ranked by popularity, maintenance and documentation.

Highest rated: private-gpt (57 614 GitHub stars, Apache-2.0 license, written in Python), followed by Omni
Docker: 2 of the top 2 ship an official Docker image
Easiest to set up: private-gpt
Recently updated: Omni v0.1.26 on 2026-09-29

Onyx alternatives compared

Project	License	Language	Stars	Docker	Setup	Latest release	Score
private-gpt	Apache-2.0	Python	57 614	Yes	Easy	v1.0.12026-06-22	81
Omni	Apache-2.0	Rust	808	Yes	Advanced	v0.1.262026-09-29	51