compare
mini-SWE-agent vs SWE-agent
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | mini-SWE-agent | SWE-agent |
|---|---|---|
| Language | Python | Python |
| Licence | MIT | MIT |
| Stars | 8.2k | 20k |
| Latest | v2.4.6 | v1.1.0 |
| Last push | 2026-10-06 | 2026-10-06 |
| Release cadence | about 7 days between releases | about 90 days between releases |
| Active contributors | 3 commit authors on the default branch in the last 90 days | 2 commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace Claude Code. Alternatives to Claude Code →
Partialmini-SWE-agentA minimal agent that works through bash commands only, aimed at benchmarks and scripting.
PartialSWE-agentTakes a GitHub issue and works on a fix with the model of your choice, aimed at autonomous runs rather than interactive sessions.
mini-SWE-agent
- v2.4.62026-07-23fix(agents): count billed calls that fail to parse against cost_limit
- v2.4.52026-07-06fix(config): read config files as UTF-8 regardless of locale
- v2.4.42026-07-02fix: remove startup-banner emoji that crashes import on non-UTF stdout
- v2.4.32026-06-29fix(run): pass the startup_command as a dict to env.execute() function.
- v2.4.22026-06-18Small release to bump image versions in programbench runner.
SWE-agent
- v1.1.02025-05-22v1.1.0: 10s of thousands of training trajectories
- v1.0.12025-02-28v1.0.1: SOTA on SWE-Bench Full
- v1.0.02025-02-13!swe_a_v1_announcement_v6
- v0.7.02024-09-25SWE-agent EnIGMA (0.7.0)
- v0.6.12024-06-20This is (mostly) a patch release, in particular fixing several issues that had been introduced by the speed improvement…
mini-SWE-agent
✓ signed The latest release, v2.4.6, carries a signature GitHub verified.
Loading the security report
SWE-agent
✓ signed The latest release, v1.1.0, carries a signature GitHub verified.
Loading the security report