alibaba/arthas
Arthas is an open-source Java diagnostic tool by Alibaba that enables real-time production troubleshooting and performance monitoring without code changes or JVM restarts.
Awesome AI Agents › Code Automation and Testing
BuilderIO/micro-agent
BuilderIO/micro-agent is an AI-powered tool designed to write and fix code by generating tests and iterating on the code until all test cases pass. It addresses the common issue with large language models (LLMs) that often produce broken or incomplete code by automating the process of test-driven development. The micro-agent concept focuses on a small, specialized AI agent that creates definitive test cases to provide clear feedback on code functionality and iterates on the code until it meets the test requirements. This approach avoids the pitfalls of general-purpose coding agents that can accumulate errors and become unreliable. The project is not intended to be a full-fledged developer replacement; it does not handle complex tasks like installing modules or managing multiple files. Instead, it concentrates on generating code that passes specific tests, making it a focused and reliable assistant for coding tasks. Users can interact with the micro-agent through a command-line interface, providing prompts and receiving code that is refined through iterative testing. Micro-agent supports integration with various large language model providers such as OpenAI, Claude, Ollama, and Groq, requiring users to configure API keys for these services. It offers features like unit test matching, where the agent runs tests after each code generation attempt to ensure correctness, and an experimental visual matching mode that helps generate code matching a given design screenshot. This visual matching is enhanced by a multi-agent approach using Anthropic Claude for feedback and OpenAI for code generation. Additionally, the micro-agent can integrate with Visual Copilot to connect directly with Figma, enabling pixel-perfect design-to-code conversion with exact reuse of components and design tokens. The tool is configurable, allowing users to set maximum iteration runs, choose different AI models, and manage API keys through a CLI configuration interface. Overall, BuilderIO/micro-agent is a specialized AI coding assistant that leverages test-driven development principles and iterative refinement to produce reliable, working code efficiently.
https://github.com/BuilderIO/micro-agent
Also in Code Automation and Testing
SWE-agent/SWE-agent
SWE-agent is an autonomous software engineering tool that uses large language models to automatically fix GitHub issues, perform web tasks, and solve cybersecurity challenges, achieving state-of-the-art results in automated software repair and offensive cybersecurity.
qodo-ai/qodo-cover
Qodo-Cover is an AI-powered tool that automates the generation of unit tests to enhance code coverage, supporting integration with GitHub CI workflows and local CLI usage.
judge0/judge0
Judge0 is a robust, scalable, and open-source online code execution system that supports over 60 programming languages and is designed for easy integration into various applications.
mattzcarey/shippie
Shippie is an AI-powered extensible code review agent that integrates into CI/CD pipelines to automatically detect code issues and improve software delivery speed.
OpenAutoCoder/Agentless
Agentless is an open-source project that automatically solves software development problems through a three-phase process of fault localization, repair, and patch validation, achieving competitive results on SWE-bench benchmarks.
the-open-engine/zeroshot
Command-line orchestrator that drives coding agent CLIs through an executor-verifier loop, so the agent that wrote a change is never the one that declares it correct.
AnandChowdhary/continuous-claude
Shell CLI that runs Claude Code in a continuous loop, opening a pull request per iteration, watching CI, merging or discarding the work, and carrying context forward through a shared markdown file.