debugging

An open-source code-review training repo with 24 AI-written bug katas in Python and JavaScript. It includes runnable tests, fix-and-verify workflows, and GitHub Actions grading for forks.

A native C++/SDL3 desktop IDE built to be driven by LLM agents, with editor, git, merge, terminal, search, and full DAP debugging workflows.

A transparent MCP proxy and terminal UI for watching real client-to-server tool calls, inspecting frames, replaying captured calls, and debugging live JSON-RPC traffic.

Mirrors turns production traces into an isolated, runnable copy of an AI agent’s environment so teams can replay workflows, reproduce bugs, and test changes safely before shipping.

Mindlas is a local-first tool for monitoring Claude Code sessions and catching agent drift before bad code lands. It offers deterministic gauges, live session tracking, correction commands, and install paths for both a plugin and PyPI/CLI use.

A macOS CLI for Firebase Crashlytics that helps AI coding agents and developers search production crashes, inspect stack traces, and measure crash impact from the terminal.

A local-first developer tool that maps code changes back to the agent session that produced them, with transcript and tool-call citations for blame and debugging.

A VS Code AI sidebar for focused coding help, with voice input, file and selection chat, Git and debugger context, and support for OpenAI-compatible, local, and budget models.

A logical KV cache profiler and leak detector for PagedAttention engines like vLLM and SGLang, with a dashboard, live engine hook, CI checks, and Perfetto trace export.

Local-first debugger for LLM agent context windows. It records each call’s context into a single-file trace so you can inspect, diff, and share what the model actually saw turn by turn.

Hydron is a hardware-native AI coding assistant for embedded engineers. It offers spec-cited code generation, datasheet-based answers, and debugging workflows tied to real hardware, with support for VS Code and CLI use.

A Claude Code mod that adds debugger-like controls for tool calls, including breakpoints, step/reject, timeline inspection, and failure diagnosis.

An open-source tool that watches Playwright failures, inspects the live page, and opens a GitHub PR with a proposed fix.

Local-first record, inspect, and replay tool for debugging AI agents. Orchid captures LLM calls and tool traffic through a proxy, exposes traces in a web UI and MCP tools, and supports offline replay for deterministic testing.

Steel’s Agent Traces turns recorded browser sessions into a readable, frame-synced timeline with inline details, markdown export, and API access for AI agent workflows.

A CLI guard for MCP stdio servers that checks for stdout pollution, handshake failures, invalid JSON-RPC frames, and startup/runtime issues before clients hit them.

BugTape is an error-tracking tool built for coding agents, capturing browser errors, failed requests, console output, and replay so an agent can inspect evidence and propose fixes over MCP.

Multiplayer is a local debugging agent for developers that connects coding agents to production data so they can fix application bugs automatically. The site highlights runtime debugging, issue deduplication, and integrations with tools like Claude Code, Codex, and Copilot.

Chrome extension that brings AI coding help directly into the browser for debugging, code explanations, security reviews, and solution generation.

Local-first CLI that records a debugging session and turns it into an evidence-backed Markdown report for PRs, handoffs, and incident notes. It captures commands, notes, exit codes, and git context, then generates a timeline and red-to-green summary from the recorded evidence.

A GitHub repository for Claude Code skills, subagents, and hooks designed to make agent work more verifiable, including regression-proof fixes, handoff notes, and installable plugin workflows.

A Superconductor blog post showing how background coding agents were used to reproduce, diagnose, and fix a Rails memory leak using derailed_benchmarks, with a reusable Agent Skill workflow included.

AgentPulse is an observability tool for multi-agent systems, with run history, crash tracking, metrics, and investigation views for reviewing agent executions.