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!
☆3,097Mar 2, 2026Updated this week
Alternatives and similar repositories for mini-swe-agent
Users that are interested in mini-swe-agent are comparing it to the libraries listed below
Sorting:
- Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.☆443Feb 27, 2026Updated last week
- SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersec…☆18,655Updated this week
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆584Updated this week
- SkyRL: A Modular Full-stack RL Library for LLMs☆1,656Updated this week
- SWE-bench: Can Language Models Resolve Real-world Github Issues?☆4,385Feb 19, 2026Updated 2 weeks ago
- Agentless🐱: an agentless approach to automatically solve software development problems☆2,011Dec 22, 2024Updated last year
- [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"☆678Mar 16, 2025Updated 11 months ago
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆251Feb 27, 2026Updated last week
- Run SWE-bench evaluations remotely☆58Aug 14, 2025Updated 6 months ago
- DSPy: The framework for programming—not prompting—language models☆32,519Updated this week
- 🙌 OpenHands: AI-Driven Development☆68,459Updated this week
- aider is AI pair programming in your terminal☆41,062Feb 25, 2026Updated last week
- Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing a…☆37,994Updated this week
- Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.☆53,029Updated this week
- verl: Volcano Engine Reinforcement Learning for LLMs☆19,519Updated this week
- Trae Agent is an LLM-based agent for general purpose software engineering tasks.☆10,919Feb 5, 2026Updated last month
- A high-throughput and memory-efficient inference and serving engine for LLMs☆71,883Updated this week
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆644Jul 29, 2025Updated 7 months ago
- Pocket Flow: 100-line LLM framework. Let Agents build Agents!☆10,132Feb 16, 2026Updated 2 weeks ago
- Universal memory layer for AI Agents☆48,604Updated this week
- A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 37.3% tasks (pass@1) in SWE-be…☆3,058Apr 24, 2025Updated 10 months ago
- ☆47Oct 28, 2025Updated 4 months ago
- 🤗 smolagents: a barebones library for agents that think in code.☆25,756Updated this week
- Lightweight coding agent that runs in your terminal☆62,963Updated this week
- ☆628Sep 1, 2025Updated 6 months ago
- Optimizing inference proxy for LLMs☆3,352Jan 28, 2026Updated last month
- an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM☆32,434Updated this week
- Our library for RL environments + evals☆3,869Feb 28, 2026Updated last week
- Open-source implementation of AlphaEvolve☆5,525Feb 4, 2026Updated last month
- Build Real-Time Knowledge Graphs for AI Agents☆23,192Updated this week
- Renderer for the harmony response format to be used with gpt-oss☆4,210Dec 15, 2025Updated 2 months ago
- AI Agent that handles engineering tasks end-to-end: integrates with developers’ tools, plans, executes, and iterates until it achieves a …☆3,505Feb 27, 2026Updated last week
- Democratizing Reinforcement Learning for LLMs☆5,167Feb 27, 2026Updated last week
- structured outputs for llms☆12,468Feb 25, 2026Updated last week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆13,451Feb 16, 2026Updated 2 weeks ago
- Structured Outputs☆13,488Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆23,905Updated this week
- Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.☆21,340Feb 24, 2026Updated last week
- The open source coding agent.☆112,841Feb 28, 2026Updated last week