mini-swe-agent
The 100-line AI agent that solves GitHub issues or helps you in your command line.
Quick Answer
AImini-SWE-agent is an open-source AI agent for developers and researchers that solves GitHub issues and assists with command-line tasks. It scores >74% on the SWE-bench verified benchmark and supports all models via LiteLLM, OpenRouter, and Portkey. Best for researchers and developers who need a minimal, hackable, and performant coding agent. Free and open-source.
mini-SWE-agent is an open-source AI agent designed for solving GitHub issues and assisting with command-line tasks. It features a minimal Python codebase, high performance on SWE-bench, and supports various local and containerized environments. The agent is free and open-source, focusing on simplicity and hackability for developers and researchers.
mini-SWE-agent is radically simpler than other agents, using only bash as a tool and maintaining a completely linear history for debugging and fine-tuning. It executes actions with independent subprocesses, making it highly stable and scalable for sandboxed environments.
Decision Intelligence
Best For
AIType
Starting Price
$0/mo
Free Trial
No
Credit Card
Not Required
Free Plan
Yes
Dimension Scores
· 5.0 avgHow good it is, across universal quality axes
Task Scores
· 5.1 avgWhat it can do, per category it works in · showing 6 of 9 tasks scoring 5+
Scores are AI-estimated from publicly available data — not an independent test or a verified user rating. How we rank →
- -Does not support custom tools beyond bash
- -Does not have different history processors
Supports all models via LiteLLM
Supports all models via OpenRouter
Supports all models via Portkey
Auto-updated
Complexity
Company Size
Team Size
Skill Level
Deployment
The Model(s) Behind It
Model details — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.
Top mini-swe-agent alternatives in the same category, ranked by quality.
Replit Agent
The best AI agent for building production-ready apps
Factory AI
Agent-native software development
Augment Code
The agentic SDLC platform for loops
Cline
AI coding, open source and uncompromised
CodeRabbit
AI code reviews — the validation layer for AI-generated code
Kiro
Move beyond AI coding to agentic engineering
Looking for more mini-swe-agent alternatives?
Explore our complete list of alternatives with filters for free, cheaper, and higher-rated options.
User Reviews
No reviews yet. Be the first to review!
Who It's For4 rolesSoftware DevelopersComputer ProgrammersWeb Developers+1 more
Platform, Content & Languages1 content types1 languagesCodeEnglish+4 more
Output Languages
Content Types
Accepts
Produces
Frequently Asked Questions
Trust Score
Insufficient data
Not enough verifiable data to score yet
Confidence: High
Reflects publicly available data, not an independent audit
No published data
Not yet checked
Some details are AI-generated estimates — verify with the vendor.
AI-generated estimate: Best For, Description, Limitations, Quick Answer, Tagline, What Makes Unique
How we source dataAI Governance & Regulatory Disclosures
Legally-sensitive fields — extracted from public vendor sources by our pipeline (Smart Generator + A3 cross-referencing) or admin-entered. Shown as claimed by the vendor; not independently audited by Intelloro.
Switching & Migration
Company Name
Princeton University & Stanford University
Based in
United States
Last major update
Jan 2024