Awesome AI Agents › Code Automation and Testing
Arthas is an open-source Java diagnostic tool developed by Alibaba that enables developers to troubleshoot production issues in Java applications without modifying code or restarting servers. It addresses the challenges of debugging in production environments where network access is limited and suspending threads for debugging is unacceptable. Arthas acts as an observer, allowing on-the-fly diagnostics without suspending existing threads or requiring JVM restarts. Key features include checking class loading status and locations, decompiling classes, viewing classloader statistics and hierarchies, monitoring method invocation details such as parameters, return values, and exceptions, tracing method calls to identify slow sub-invocations, and monitoring system metrics like CPU usage, thread states, and garbage collection statistics. Arthas supports interactive command-line usage with auto-completion, remote diagnostics via telnet and websocket, and profiling with flame graphs. It can retrieve objects from the heap by class instance and supports JDK 6 and above on Linux, Mac, and Windows platforms. Arthas provides a dashboard for visualizing system and application metrics, thread analysis to identify CPU usage hotspots, and a decompiler for inspecting class bytecode. It is designed to be easy to install and use, with quick start options including a bootstrap jar and shell script installer. Comprehensive documentation, tutorials, and user cases are available online. Arthas is widely used for real-time production troubleshooting, performance monitoring, and debugging in Java environments, making it a valuable tool for developers and operations teams to maintain application reliability and performance without downtime or code changes.
https://github.com/alibaba/arthas
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-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 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.
BuilderIO/micro-agent is an AI-powered tool that writes and iteratively refines code by generating tests and ensuring all test cases pass, focusing on reliable test-driven development.
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.
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.
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.
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.