Leonxlnx/taste-skill
Taste Skill provides portable AI Agent Skills designed to enhance the quality of AI-generated frontends and image-based design references, aiming to eliminate generic UI outputs.
Awesome AI Agents › AI Developer Toolkit
SWE-agent/SWE-ReX
SWE-ReX is a remote execution framework designed to provide a runtime interface for interacting with sandboxed shell environments. It enables AI agents to execute any command on any environment seamlessly, whether locally or remotely, including Docker containers, AWS remote machines, Modal, and more. The framework supports massively parallel execution, allowing hundreds of agents to run simultaneously without performance degradation. SWE-ReX facilitates interaction with running shell sessions by recognizing command completion, extracting output and exit codes, and returning these results to the agent. It also supports the use of interactive command-line tools such as ipython and gdb within these shell sessions. Multiple shell sessions can be managed in parallel, mimicking the human ability to operate various tools concurrently. The project aims to abstract infrastructure complexities from agent development, making it easier to develop and evaluate AI agents without worrying about the underlying execution environment. SWE-ReX originated from the experiences with SWE-agent and SWE-agent enigma projects, focusing on fast, scalable, and stable agent execution across diverse platforms, including non-Linux systems without Docker. It is designed to disentangle agent logic from infrastructure concerns, enhancing stability and maintainability. The framework is actively maintained with continuous integration workflows for testing, link checking, and documentation building. Installation is straightforward via pip, with optional dependencies for Modal and AWS Fargate support. SWE-ReX is part of a broader ecosystem including SWE-agent, SWE-bench, SWE-smith, and sb-cli, all aimed at advancing AI agent development and benchmarking. The project is well-documented and supported, making it a robust choice for developers needing scalable, flexible, and easy-to-extend remote execution capabilities for AI agents.
https://github.com/SWE-agent/SWE-ReX
Also in AI Developer Toolkit
unslothai/unsloth
Unsloth is a toolkit for fine-tuning and reinforcement learning of large language models, enabling faster training with significantly reduced VRAM usage across various advanced models and tasks.
reworkd/AgentGPT
AgentGPT is an open-source platform that allows users to assemble, configure, and deploy autonomous AI agents in a web browser to pursue custom goals by generating and executing tasks independently.
Gitlawb/openclaude
OpenClaude is an open-source command-line interface (CLI) coding-agent that supports various cloud and local model providers for unified AI-driven development workflows.
virgiliojr94/book-to-skill
A command-line tool that converts technical books, document folders or globs into structured agent skills in the open SKILL.md format, so coding agents load only the chapter relevant to a question.
google/adk-python
An open-source Python toolkit by Google for building, evaluating, and deploying sophisticated AI agents with flexibility, modularity, and integration within the Google ecosystem.
can1357/oh-my-pi
Oh My Pi is an AI coding agent for the terminal featuring hash-anchored edits, an optimized tool harness, LSP integration, and support for Python, browsers, and subagents.
millionco/react-doctor
React Doctor is an intelligent agent designed to diagnose and fix issues within React codebases, leveraging AI to improve code quality and developer efficiency.