LocalAI vs Onyx Community Edition

Both are self-hosted generative artificial intelligence (genai) projects. This page compares how well each one is actually maintained — the part you cannot see from a feature list.

LocalAI and Onyx Community Edition are closely matched on maintenance health (97 vs 94). Neither is the safer bet on activity alone, so choose on features, licence and the stack you already run.
LocalAIOnyx Community Edition
Health score 97/100 94/100
Commits (11 mo) 2821 5483
Commits (last 3 mo) 1205 1694
Stars 49k 32k
Latest release 17 Sept 2026 27 Sept 2026
Licence MIT MIT
Built with Docker, K8S Docker, K8S
Typical RAM 2 GB 2 GB

LocalAI

Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).

97/100
Thriving

High commit volume, frequent releases and growing activity.

Maintenance 37/40
Releases 25/25
Community 19/20
Momentum 15/15

Commit activity more than 93% of tracked projects; popularity more than 97%. How this is calculated.

Commits, last 11 months

2025-10: 0 commits 2025-11: 163 commits 2025-12: 195 commits 2026-01: 182 commits 2026-02: 179 commits 2026-03: 272 commits 2026-04: 288 commits 2026-05: 337 commits 2026-06: 365 commits 2026-07: 461 commits 2026-08: 379 commits

Onyx Community Edition

Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.

94/100
Thriving

High commit volume, frequent releases and growing activity.

Maintenance 39/40
Releases 25/25
Community 18/20
Momentum 12/15

Commit activity more than 97% of tracked projects; popularity more than 92%. How this is calculated.

Commits, last 11 months

2025-10: 274 commits 2025-11: 295 commits 2025-12: 478 commits 2026-01: 546 commits 2026-02: 567 commits 2026-03: 559 commits 2026-04: 556 commits 2026-05: 514 commits 2026-06: 612 commits 2026-07: 640 commits 2026-08: 442 commits

How to read this

Everything above is measured, not opinion: commit counts and release dates come from the public repositories, and the health score ranks each project against all 1352 projects we track. Read the full method.

What this comparison deliberately does not do is tell you which has the better feature set. Maintenance health tells you which project will still be receiving security fixes in two years. Decide that first, then compare features on the projects that survive the filter.

See every option in this category: self-hosted generative artificial intelligence (genai).