head to head · open source
T3 Code vs SWE-agent
T3 Code has 41,350 GitHub stars, 9,068 forks, 1,628 open issues and last shipped yesterday. SWE-agent has 20,712 stars, 2,264 forks, 102 open issues and last shipped 8 days ago. T3 Code leads on adoption by 100% (41,350 vs 20,712 stars). T3 Code is written in TypeScript under MIT; SWE-agent is written in Python under MIT. T3 Code has attracted 22% as many forks as stars, SWE-agent 11%. T3 Code 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.
← all 20902 open source comparisons
Side by side
| T3 Code | SWE-agent | |
|---|---|---|
| GitHub stars | ★ 41K | ★ 21K |
| License | MIT | MIT |
| Written in | TypeScript | Python |
| Last push | 2026-11-02 | 2026-10-26 |
| Forks | ⑂ 9.1K | ⑂ 2.3K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick T3 Code if
- You weight community size — 41K stars and counting
- You want the MIT license terms
- Your stack matches TypeScript
- 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 T3 Code
T3 Code T3 Code is an "agent harness control surface". It enables control of the agents on your machine with a best in class mobile app (iOS, Android), web app and Electron based desktop app. Works with your subscriptions on Claude Code, Codex, Cursor, Grok Build, OpenCode, and Google Antigravity. If they're set up on your computer, T3 Code can control them. "Wait, what are you selling me?" Nothing. We built T3 Code because we wanted the best possible development experience with agents. We were inspired by existing solutions like the Codex desktop app, Conductor, Claude Desktop and Cursor Glass, but none met our…
read the full T3 Code overview →
About SWE-agent
[!warning] Most of our current development effort is on mini swe agent, which has superseded SWE agent. It matches the performance performance of SWE agent, while being much simpler. See the FAQ for more details about the differences. Our general recommendation is to use mini SWE agent instead of SWE agent going forward. SWE agent enables your language model of choice (e.g. GPT 4o or Claude Sonnet 4) to autonomously use tools to fix issues in real GitHub repositories, find cybersecurity vulnerabilities, or perform any custom task. ✅ State of the art on SWE bench among open source projects ✅ Free flowing &…
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 T3 Code or SWE-agent more popular?
T3 Code has 41,350 GitHub stars and SWE-agent has 20,712. T3 Code has the larger community by that measure.
Are T3 Code and SWE-agent free?
Both are open source. T3 Code is licensed under MIT and SWE-agent under MIT. Neither carries a licence fee.
What is the difference between T3 Code and SWE-agent?
T3 Code is written in TypeScript 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, T3 Code or SWE-agent?
Choose T3 Code if you want the larger community (41,350 stars) or its MIT licence terms. Choose SWE-agent if its feature set, stack or MIT licence fits better. Both are self-hostable.