head to head · open source

T3 Code vs SWE-agent

T3 Code has 22,945 GitHub stars, 5,817 forks, 1,628 open issues and last shipped yesterday. SWE-agent has 20,344 stars, 2,224 forks, 102 open issues and last shipped 4 days ago. T3 Code leads on adoption by 13% (22,945 vs 20,344 stars). T3 Code is written in TypeScript under MIT; SWE-agent is written in Python under MIT. T3 Code has attracted 25% 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.

T3 Code ★ 23K SWE-agent ★ 20K category Developer Tools

← all 8884 open source comparisons

Side by side

T3 Code SWE-agent
GitHub stars ★ 23K ★ 20K
License MIT MIT
Written in TypeScript Python
Last push 2026-09-17 2026-09-14
Forks ⑂ 5.8K ⑂ 2.2K
Self-hosting Yes Yes
Data ownership Your server Your server

pick T3 Code if

  • You weight community size — 23K stars and counting
  • You want the MIT license terms
  • Your stack matches TypeScript
  • You value the larger contributor base for long-term maintenance

full T3 Code profile →

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

full SWE-agent profile →

About T3 Code

T3 Code is an open source agent harness control surface for AI assisted coding. It lives in the developer tools ecosystem for local coding agents, and it gives users one interface for agents that are already installed and authenticated on their own computer. The project is written in TypeScript and is MIT licensed.

read the full T3 Code 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

OpenCode ★ 208K Langflow ★ 155K Supabase ★ 110K pi ★ 107K fastapi ★ 102K Neovim ★ 102K

Related comparisons

opencode vs pi opencode vs openhands opencode vs paperclip opencode vs orca opencode vs cline opencode vs aider opencode vs continue opencode vs tabby opencode vs neovim opencode vs zed langflow vs neovim langflow vs zed opencode vs kilocode opencode vs codeedit neovim vs zed langflow vs kilocode langflow vs supabase langflow vs pocketbase langflow vs tooljet langflow vs appsmith langflow vs tiptap langflow vs directus langflow vs budibase langflow vs onlook

More AI Assisted Coding projects

Compare either of these against the rest of the AI Assisted Coding field.

T3 Code vs OpenCode T3 Code vs pi T3 Code vs OpenHands T3 Code vs Paperclip T3 Code vs Orca T3 Code vs Cline T3 Code vs Aider T3 Code vs Continue T3 Code vs Tabby T3 Code vs Grok Build T3 Code vs Dyad T3 Code vs Paseo

Frequently asked questions

Is T3 Code or SWE-agent more popular?

T3 Code has 22,945 GitHub stars and SWE-agent has 20,344. 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 (22,945 stars) or its MIT licence terms. Choose SWE-agent if its feature set, stack or MIT licence fits better. Both are self-hostable.