SWE-agent/mini-swe-agent
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #28 among AI Agents repositories ranked this week, and #31 over the last 30 days; #100 of 163 repositories with measured growth this week (top 61%).
This week's +446 stars is ahead of its 30-day pace of about +245 per week.
No releases in the last 90 days; the most recent was 108 days ago, with 39 contributors on GitHub.
Peaked at #100 in the weekly ranking the week of Nov 8, its best in the past year.
Use Cases & Benefits
- mini-swe-agent is a minimal AI agent in Python designed to solve GitHub issues and assist in command line tasks with a simple, 100-line codebase.
- Key features include no heavy dependencies, bash-only tool usage, subprocess-based action execution, linear message history, and >74% score on SWE-bench verified benchmark.
- Strengths are simplicity, fast startup, easy sandboxing, and high performance; limitations include lack of built-in tools beyond bash and minimal configuration options.
- Organizations can deploy mini-swe-agent locally or in containers for lightweight, stable AI-assisted automation and benchmarking, especially useful for research and fine-tuning.
- Ideal use cases are researchers benchmarking or fine-tuning AI agents, developers wanting hackable CLI tools, and engineers needing simple, deployable AI agents for software engineering tasks.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
- Code of conduct: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
In 2024, we built SWE-bench & SWE-agent and helped kickstart the coding agent revolution.
We now ask: What if our agent was 100x smaller, and still worked nearly as well?
The
miniagent is formodel, and run script) — no fancy dependencies!
Option 1: If you just want to try out the CLI (package installed in anonymous virtual environment)
Option 2: Install CLI & python bindings in current environment
Option 3: Install from source (developer setup)
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+2,643 stars over 75 days across 12 snapshot days; best day +30 on Oct 5.
Forks
1.3K+353
Open issues
140+85
Compared with peers in AI Agents
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 8, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| morluto/rea | 450.0K | +22.9K | 75 | 16 days ago |
| vercel-labs/agent-desktop | 21.4K | +8.7K | 75 | 5 days ago |
| milind-soni/OpenMausBot | 20.6K | +8.4K | 75 | today |
| stablyai/orca | 121.4K | +6.7K | 75 | today |
| thedotmack/claude-mem | 115.8K | +4.7K | 75 | today |
| SWE-agent/mini-swe-agent | 9.4K | +446 | 52 | 108 days ago |
| Category median | 115.8K | +8.4K | 75 | — |
Discover Repositories
Search across tracked repositories by name or description