- fix(agents): count billed calls that fail to parse against cost_limit
mini-SWE-agent by Princeton University & Stanford University (SWE-agent team)
Open-source software-engineering agents from Princeton and Stanford researchers: SWE-agent (2024) and its roughly 100-line successor mini-SWE-agent, which uses only bash and works with any model through LiteLLM and similar routers. The SWE-agent README says development effort has moved to mini-SWE-agent.
Use it in: CLI Works with: Local models Own API key Headless / CI
On this page
Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number
What mini-SWE-agent does
mini-SWE-agent is a terminal agent (research) from Princeton University & Stanford University, first released in April 2024. You use it through a command-line tool. Its documentation covers a non-interactive mode for scripts and CI, your own API key and local models. It can run models from Anthropic, OpenAI, OpenRouter and any OpenAI-compatible endpoint. It is free and open source (MIT); you pay only for the models it calls.
Status: As of 2026-10-05 the SWE-agent README says it has been superseded by mini-SWE-agent (last SWE-agent release v1.1.0 on 2025-05-22).
Recent developments
- 2026-02-02: mini-SWE-agent v2 first alpha published on PyPI (2.0.0a1)
Key facts
| Maker | Princeton University & Stanford University (SWE-agent team) |
|---|---|
| Type | Terminal agent (research) |
| First released | April 2024 |
| License | MIT |
| Interfaces | CLI |
| Models | Any model via LiteLLM, OpenRouter, Portkey and similar |
| Local models | Local servers such as vLLM through LiteLLM (docs) |
| Bring your own API key | Yes |
| Main language | Python |
| Open issues and PRs | 147 |
Pricing
Free MIT-licensed research software; users pay their model provider through their own API keys.
Checked Nov 4, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (MIT)
- Works with local models?Yes
- Bring your own API key?Yes
- Where you use itCLI
- Model providersanthropic, openai, openrouter, any OpenAI-compatible, local
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativeClaude Code · all alternatives
What's new in mini-SWE-agent: July 2026
July brought stability improvements to mini-SWE-agent, with fixes addressing import crashes, configuration handling, and cost tracking accuracy.
- Fixed startup crashes on systems without UTF-8 support
- Configuration files now read consistently as UTF-8 across all locales
- Tool-call errors are now reported accurately instead of being misidentified as truncation
- Failed API calls are now correctly counted toward cost limits
3 releases this month · summarised from the official release notes · all months
AgentGid articles about mini-SWE-agent
AI Agent Statistics 2026: Live Usage, Growth and Activity Data
Current statistics on AI agents from public data: package downloads, editor installs, GitHub stars, pull requests opened by coding agents, release pace and benchmark results. Updated daily.
How to Start Using a Terminal Coding Agent: Setup, First Tasks and Guardrails
A practical manual for your first week with a command-line coding agent: installing one, running a first session, writing project instructions, setting permissions and keeping costs under control.
Get started with mini-SWE-agent
| PyPI | pip install mini-swe-agent |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
mini-SWE-agent alternatives
Best mini-SWE-agent alternatives compared · All terminal coding agents
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
Claude CodeAnthropic |
88 | 18.9M | up 15.1% | up 15.5% | 156K+136/day | 2.1.328yesterday | $20/mo | |||
| 2 |
OpenAI CodexOpenAI |
84 | 26.6M | up 2.4% | up 7.4% | 136K+144/day | 0.168.07d ago | Free + $8/mo | |||
| 3 |
OpenCodeAnomaly (SST team) |
80 | 3.9M | up 15.4% | up 28.7% | 228K+266/day | 2.3.22d ago | Free + $10/mo | |||
| 7 |
PiEarendil Inc. (created by Mario Zechner) |
73 | 6.4M | up 1.6% | up 36.3% | 123K+193/day | 1.5.210d ago | Free (OSS) | |||
| 15 |
Gemini CLIGoogle |
62 | 495K | up 16.9% | up 6.8% | 109K+35/day | 0.69.0yesterday | API usage or license | |||
| 20 |
ClineCline Bot Inc. |
58 | 84.3K | down 8.7% | up 14.9% | 71.8K+38/day | 4.1.2625d ago | Free + $9.99/mo | |||
Head to head: mini-SWE-agent vs Claude Code · mini-SWE-agent vs OpenAI Codex · mini-SWE-agent vs OpenCode · mini-SWE-agent vs Pi
Ratings from people who use mini-SWE-agent
No ratings yet. Used mini-SWE-agent? Rate it and say what it is good and bad at.
What changed: recent mini-SWE-agent releases
- fix(config): read config files as UTF-8 regardless of locale
- fix(models): don't mask malformed tool-call errors as truncation
Earlier releases
- fix: remove startup-banner emoji that crashes import on non-UTF stdout
- fix(benchmarks): don't mutate shared config across worker threads in get_sb_environment
- @EnesYilmazcode made their first contribution in
- fix(run): pass the startup_command as a dict to env.execute() function.
- Reject empty config override keys
- @Ethan-Kuang-6666 made their first contribution in
- @CodingFeng101 made their first contribution in
- Update: programbench uses v6 images
- fix: kill local process group on timeout
- @Swing-G made their first contribution in
- maaz139 for reporting the timeout bug
mini-SWE-agent prices over time
mini-SWE-agent popularity and usage data
mini-SWE-agent was downloaded 3.1M times from PyPI in the week ending Nov 17, 2026, down 3.5% on the week before and down 1.7% over the last 30 days compared with the 30 before. The GitHub repository has 9,771 stars, 1,130 of them added in the last 30 days. The latest stable release is 2.4.6, published Jul 23, 2026. On Terminal-Bench 4.1 its best listed result is 91.0% with Inkling Small, ranking 1 of 7 agents on that board. It was mentioned in 5 Hacker News posts and comments over the last 30 days.
Download the raw daily series: mini-swe-agent.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| Package downloads | Nov 17, 2026 | Nov 19, 06:24 UTC |
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Hacker News mentions | Nov 18, 2026 | Nov 19, 06:26 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
mini-SWE-agent benchmark results
| Benchmark | Model | Effort | Tasks solved | Cost of run | Place |
|---|---|---|---|---|---|
| Terminal-Bench 4.1 | Inkling Small | none | 91.0% ± 94.0 | $50 | #1 of 7 |
| Nemotron 3.5 Super VL | none | 30.0% ± 59.0 | $167 | ||
| MiMo V2.6 Pro | none | 27.0% ± 3.6 | $282 | ||
| Ember-1 | none | 21.8% ± 3.5 | $4,718 | ||
| Terminal-Bench 4.0 | Inkling Small | none | 91.0% ± 94.0 | $50 | #1 of 6 |
| Nemotron 3.5 Super VL | none | 30.0% ± 59.0 | $167 | ||
| MiMo V2.6 Pro | none | 27.0% ± 3.6 | $282 | ||
| Ember-1 | none | 21.8% ± 3.4 | $4,718 | ||
| Terminal-Bench 3.0 | Opus 5 | max | 42.7% ± 3.1 | $5,818 | #1 of 6 |
| Terminal-Bench 2.1 | Muse Spark 1.1 | xhigh | 76.2% ± 2.4 | $198 | #5 of 6 |
| Terminal-Bench 2.0 | Claude Sonnet 4.5 | — | 42.5% ± 2.8 | — | #40 of 43 |
| GPT-5-Codex | — | 41.4% ± 2.8 | — | ||
| Claude Opus 4.1 | — | 35.1% ± 2.5 | — | ||
| GPT-5 | — | 33.9% ± 2.9 | — |
Up to four best runs per board. Scores are not comparable between Terminal-Bench versions. Source: Terminal-Bench (tbench.ai).
mini-SWE-agent FAQ
How much does mini-SWE-agent cost?
Free MIT-licensed research software; users pay their model provider through their own API keys.
Is mini-SWE-agent open source?
Yes. mini-SWE-agent is open source, released under the MIT license.
How popular is mini-SWE-agent?
mini-SWE-agent was downloaded 3.1M times from PyPI in the week ending Nov 17, 2026, down 3.5% on the week before and down 1.7% over the last 30 days compared with the 30 before. The GitHub repository has 9,771 stars, 1,130 of them added in the last 30 days. The latest stable release is 2.4.6, published Jul 23, 2026.
What is the latest version of mini-SWE-agent?
The latest stable release we track is 2.4.6, published on Jul 23, 2026.
What are the alternatives to mini-SWE-agent?
The closest alternatives in the same category by Gid Score are Claude Code, OpenAI Codex, OpenCode, Pi.
For the makers of mini-SWE-agent badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/mini-swe-agent/)
[](https://agentgid.com/agents/mini-swe-agent/)
[](https://agentgid.com/agents/mini-swe-agent/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
PyPI: mini-swe-agent. GitHub: SWE-agent/mini-swe-agent. Site rank: mini-swe-agent.com on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: github.com, pypi.org, mini-swe-agent.com.