head to head · open source

Onyx vs atmos

Onyx has 33,170 GitHub stars, 4,692 forks, 451 open issues and last shipped yesterday. atmos has 1,409 stars, 197 forks, 289 open issues and last shipped yesterday. Onyx leads on adoption by 2,254% (33,170 vs 1,409 stars). Onyx is written in Python under a custom or non-standard licence; atmos is written in Go under Apache-2.0. Onyx has attracted 14% as many forks as stars, atmos 14%. Onyx was the more recently maintained of the two, and both are self-hostable with no licence fee.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

Onyx ★ 33K atmos ★ 1.4K category AI & Machine Learning

← all 20902 open source comparisons

Side by side

Onyx atmos
GitHub stars ★ 33K ★ 1.4K
License Custom / other Apache-2.0
Written in Python Go
Last push 2026-11-02 2026-11-02
Forks ⑂ 4.7K ⑂ 197
Self-hosting Yes Yes
Data ownership Your server Your server

pick Onyx if

  • You weight community size — 33K stars and counting
  • You want the Custom / other license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full Onyx profile →

pick atmos if

  • You want the atmos feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches Go
  • You evaluated both and atmos fits your workflow better

full atmos profile →

About Onyx

Onyx The Open Source AI Platform Onyx is the application layer for LLMs bringing a feature rich interface that can be easily hosted by anyone. Onyx enables LLMs through advanced capabilities like RAG, web search, code execution, file creation, deep research and more. Connect your applications with over 50+ indexing based connectors provided out of the box or via MCP. [!TIP] Deploy with a single command: ⭐ Features 🔍 Agentic RAG: Get best in class search and answer quality based on hybrid index + AI Agents for information retrieval Benchmark to release soon! 🔬 Deep Research: Get in depth reports with a multi…

read the full Onyx overview →

About atmos

Run your infrastructure anywhere. Atmos is the open source runtime for infrastructure — it builds, authenticates, and ships Terraform, OpenTofu, Kubernetes, Helm, and containers the same way on your laptop, in CI, and with AI agents. Auth, secrets, vendoring, caching, the toolchain, workflows, and CI are built in. Point every environment at the same reusable root modules and treat the rest as configuration. Stop stringing together 25 tools. Run it on your laptop. Run it the same in CI. Run it with agents. Everything is open source and free. [!TIP] You can try out atmos directly in your browser using GitHub…

read the full atmos overview →

More in AI & Machine Learning

Related comparisons

More AI Interaction & Interfaces projects

Compare either of these against the rest of the AI Interaction & Interfaces field.

Frequently asked questions

Is Onyx or atmos more popular?

Onyx has 33,170 GitHub stars and atmos has 1,409. Onyx has the larger community by that measure.

Are Onyx and atmos free?

Both are open source. Onyx has no licence declared in this registry, and atmos is licensed under Apache-2.0. Both are free to self-host.

What is the difference between Onyx and atmos?

Onyx is written in Python and atmos in Go. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, Onyx or atmos?

Choose Onyx if you want the larger community (33,170 stars) or its Custom / other licence terms. Choose atmos if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.