Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

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.

Terminal coding agents Terminal agent (research)Open source · MITFree to start

Use it in: CLI Works with: Local models Own API key Headless / CI

Price
Free (OSS)
free and open source
Popularity
#11 in Terminal
Gid Score 51 / 100 · #40 of 251 ranked AI agents
Trend
Steady
downloads down 1.7% over 30 days · down 3.5% last week
Development
Quiet lately
latest 2.4.6, 4mo ago
Community
9,771 GitHub stars
3.1M package downloads a week

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Status: As of 2026-10-05 the SWE-agent README says it has been superseded by mini-SWE-agent (last SWE-agent release v1.1.0 on 2025-05-22).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

MakerPrinceton University & Stanford University (SWE-agent team)
TypeTerminal agent (research)
First releasedApril 2024
LicenseMIT
InterfacesCLI
ModelsAny model via LiteLLM, OpenRouter, Portkey and similar
Local modelsLocal servers such as vLLM through LiteLLM (docs)
Bring your own API keyYes
Main languagePython
Open issues and PRs147

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.

Compare prices of all agents

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

Full monthly summary

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

All guides

Get started with mini-SWE-agent

PyPIpip install mini-swe-agent

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare mini-SWE-agent with another agent

vs
# 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 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 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

Monthly summary · Full changelog

2.4.6
  • fix(agents): count billed calls that fail to parse against cost_limit
2.4.5
  • fix(config): read config files as UTF-8 regardless of locale
  • fix(models): don't mask malformed tool-call errors as truncation
Earlier releases
2.4.4
  • 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
2.4.3
  • 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
2.4.2
  • Update: programbench uses v6 images
2.4.1
  • 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

Token prices of Anthropic modelsnewest Anthropic model in each family, output price per 1M tokens
Anthropic OpusAnthropic SonnetAnthropic Haiku

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.

Downloads per dayPyPI, 7-day average 440K/day
GitHub starsrunning total 9,771
Hacker News mentionsposts and comments, rolling 7-day total 2 this week

Download the raw daily series: mini-swe-agent.csv

Gid Score breakdown

Adoption78
Community41
Attention0
Momentum48

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

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 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

All agents on Terminal-Bench

BenchmarkModelEffortTasks solvedCost of runPlace
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:

AgentGid: #11 in Terminal Gid Score: 51/100 downloads: 3.1M/week ▼2% 30d

[![AgentGid: #11 in Terminal](https://agentgid.com/badges/mini-swe-agent-rank.svg)](https://agentgid.com/agents/mini-swe-agent/)
[![Gid Score: 51/100](https://agentgid.com/badges/mini-swe-agent-score.svg)](https://agentgid.com/agents/mini-swe-agent/)
[![downloads: 3.1M/week ▼2% 30d](https://agentgid.com/badges/mini-swe-agent-downloads.svg)](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.