head to head · open source
Tabby vs SWE-agent
Tabby has 33,884 GitHub stars, 1,788 forks, 335 open issues and last shipped 3 months ago. SWE-agent has 20,344 stars, 2,224 forks, 102 open issues and last shipped 4 days ago. Tabby leads on adoption by 67% (33,884 vs 20,344 stars). Tabby is written in Rust under a custom or non-standard licence; SWE-agent is written in Python under MIT. Tabby has attracted 5% as many forks as stars, SWE-agent 11%. SWE-agent was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (ai, developer-tools), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 8884 open source comparisons
Side by side
| Tabby | SWE-agent | |
|---|---|---|
| GitHub stars | ★ 34K | ★ 20K |
| License | Custom / other | MIT |
| Written in | Rust | Python |
| Last push | 2026-06-30 | 2026-09-14 |
| Forks | ⑂ 1.8K | ⑂ 2.2K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick Tabby if
- You weight community size — 34K stars and counting
- You want the Custom / other license terms
- Your stack matches Rust
- You value the larger contributor base for long-term maintenance
pick SWE-agent if
- You want the SWE-agent feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and SWE-agent fits your workflow better
About Tabby
Tabby is a self hosted, open source AI coding assistant that acts as an on premises alternative to GitHub Copilot, aimed at developers and engineering teams that want code completion and chat without routing source code through a third party cloud service.
read the full Tabby overview →
About SWE-agent
SWE agent is a Python, MIT licensed open source project in the AI assisted coding and agent ecosystem. It is an agent based model for developer tools that takes a GitHub issue and tries to automatically fix it using a chosen language model. The project is associated with NeurIPS 2024 and is maintained by researchers from Princeton University and Stanford University.
read the full SWE-agent overview →
More in Developer Tools
Related comparisons
More AI Assisted Coding projects
Compare either of these against the rest of the AI Assisted Coding field.
Frequently asked questions
Is Tabby or SWE-agent more popular?
Tabby has 33,884 GitHub stars and SWE-agent has 20,344. Tabby has the larger community by that measure.
Are Tabby and SWE-agent free?
Both are open source. Tabby has no licence declared in this registry, and SWE-agent is licensed under MIT. Both are free to self-host.
What is the difference between Tabby and SWE-agent?
Tabby is written in Rust and SWE-agent in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, Tabby or SWE-agent?
Choose Tabby if you want the larger community (33,884 stars) or its Custom / other licence terms. Choose SWE-agent if its feature set, stack or MIT licence fits better. Both are self-hostable.