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
vanzan01/claude-code-sub-agent-collective
Claude Code Sub-Agent Collective is an experimental npm package, installed with npx claude-code-collective init, that provisions a whole team of Claude Code sub-agents inside an existing repository. The installer writes a CLAUDE.md with behavioral rules, a .claude directory holding more than 30 agent definition files, hook scripts and settings, and a .claude-collective directory with Vitest-based test templates and usage metrics. The agents are grouped by role: implementation agents for UI components, business logic, infrastructure, test suites and performance polish; quality agents for code review, deployment, Playwright browser testing and completion gates; and research agents that pull library documentation through Context7 instead of relying on model recall. Coordination follows a hub-and-spoke design. A /van slash command routes a request to a task-orchestrator agent, which analyses the request, breaks it into work items, decides what can run in parallel and delegates each item to the matching specialist. Every implementation agent is bound to the same contract: write failing tests first, add the minimum code that turns them green, refactor while the suite stays green, and report the test counts back at handoff. Shell hooks such as test-driven-handoff.sh enforce that sequence rather than leaving it to prompt discipline. Install modes let a user take only the core agents, only the testing framework, only the hooks, or run an interactive selection. The author describes the project as opinionated research into context engineering, built to speed up his own prototype work, so behaviour can change between releases and the metrics collection exists for the project's own development. It suits developers who already work in Claude Code and want an enforced test-first pipeline and automatic task decomposition rather than ad-hoc prompting.
https://github.com/vanzan01/claude-code-sub-agent-collective
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.
BuilderIO/micro-agent
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.
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.