OpenHands/OpenHands
OpenHands is an AI-powered platform that automates software development tasks, enabling developers to code less and produce more by modifying code, running commands, browsing the web, and integrating APIs efficiently.
SWE-agent/mini-swe-agent
mini-swe-agent is a minimalistic AI agent designed to solve GitHub issues and assist users in command line environments. It is remarkably compact, consisting of just 100 lines of Python code, making it radically simple without complex configurations or large monolithic codebases. Despite its simplicity, it achieves a 65% success rate on the SWE-bench verified benchmark, demonstrating its effectiveness. The project targets researchers, developers, and engineers who seek a lightweight, easy-to-understand, and deployable AI agent. It is ideal for benchmarking, fine-tuning, reinforcement learning, and daily development workflows. The agent operates solely with bash commands, avoiding the need for additional tools or dependencies, which enhances its portability and ease of use in sandboxed environments. It maintains a linear history of interactions, appending each step to the message log, which simplifies debugging and fine-tuning. Actions are executed independently using subprocess.run, allowing for stable and scalable execution, including in containerized environments like Docker or Podman. The project is backed by the Princeton and Stanford teams behind SWE-bench and SWE-agent, ensuring cutting-edge research and development. It offers simple and visual user interfaces, batch inference capabilities, and a trajectory browser for analyzing agent behavior. The project is well-documented and tested, with a focus on being a hackable tool rather than a black box, emphasizing simplicity, convenience, and flexibility. It is suitable for users who want a straightforward, local command line tool with a simple control flow and fast sandboxing, while those needing more complex tool integrations or configurations might prefer the full SWE-agent. Overall, mini-swe-agent is a powerful yet minimal AI agent that leverages language models and shell commands to automate issue resolution and command line tasks efficiently.
https://github.com/SWE-agent/mini-swe-agent
Also in AI Agents
usestrix/strix
Strix is an open-source AI-driven security testing platform that autonomously finds, validates, and helps fix application vulnerabilities through dynamic and collaborative AI agents.
aaif-goose/goose
Goose is an open-source, native AI agent available as a desktop app, CLI, and API, designed for diverse tasks like code, research, writing, and automation, supporting over 15 LLM providers.
KeygraphHQ/shannon
Shannon is an autonomous AI pentester for web applications and APIs, analyzing source code, identifying attack vectors, and executing real exploits to prove vulnerabilities.
wshobson/agents
A comprehensive collection of 44 specialized AI subagents for Claude Code that enhance development workflows with domain-specific expertise across software development, infrastructure, security, data, and business domains.
agentscope-ai/agentscope
AgentScope is a transparent, modular, and customizable framework for building LLM-empowered multi-agent applications with real-time control and asynchronous execution.
iOfficeAI/OfficeCLI
OfficeCLI is an open-source command-line interface and API enabling AI agents to read, edit, and automate Word, Excel, and PowerPoint files without needing Office suite installations.
langchain-ai/deepagents
Deep Agents is an open-source agent harness built on LangChain and LangGraph that enables AI agents to plan, execute, and delegate complex long-horizon tasks using customizable tools, subagents, and human-in-the-loop workflows.