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!
Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.
Appears on
Quick read
Latest capture 2026-08-03 03:02
0 paths
Agent instructions and tool configuration found in this repository.
No config files detected.
6 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +53
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
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!
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
SWE-bench: Can Language Models Resolve Real-world Github Issues?
swebench repro script for running confucius-code-agent (CCA)
An Open-Source Asynchronous Coding Agent
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.