The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.

Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns manual steps, tool calls, LLM calls, structured logs, failures, durations, and run metadata into readable execution trees you can inspect from the terminal. It is built for TypeScript/Node.js developers..

Drive x64dbg with your AI. MCP server: 23 mega-tools / 153 endpoints for breakpoints, memory, disasm, tracing, anti-debug & PE dumping. Claude/Cursor/Windsurf/Cline. All local.

A stop-loss for Claude Code: detects loops, compaction danger, failed tools, and token waste before the next request.

Local-first situational awareness layer for AI agents. Single binary, written in Rust.

🤖 An AI-native MCP server for .NET memory dump investigations. Leverage LLMs (Claude/Gemini) to analyze heaps, threads, and exceptions using natural language. Built with ClrMD, token-efficient paging, and Docker support for cross-architecture (.NET/AMD64/ARM64) post-mortem analysis.

Local-first agent debugger with replay, failure memory, smart highlights, and drift detection.

Codex CLI session supervision: see failed or incomplete turns, token use, model changes, context pressure, and postmortems.

AI-Powered Execution Cinema Debugger for Elixir/BEAM

ai agent

Local visual debugger for AI agent runs: replay failures, inspect prompts/tools/results, and export redacted evidence.

Claude Code skill + CLI that lets an AI agent drive Rider's MCP debugger to debug a running Unity Editor at runtime, no session restart needed.

🩺 RAG Doctor — Open-source diagnostic tool for Retrieval-Augmented Generation (RAG) systems. Analyzes codebases to detect architectural issues in LLM pipelines such as missing retrieval, bad chunking, embedding mismatches, and vector database misuse.

MCP server for rr reverse debugging — enables AI assistants to record, replay, and inspect program executions via GDB/MI

QA Continuity AI — a private, on-premise platform that turns scattered project knowledge (rules, flows, bugs, tests, CI) into test plans, Playwright automation, and searchable QA memory. 100% local LLMs via Ollama + HuggingFace, zero API cost.

AI-assisted MCU debug automation framework / AI 辅助 MCU 自动调试框架

Quick entry for the WFGY AI Troubleshooting Atlas. Fast links, quick start, and a 60-second try. Part of the WFGY ecosystem.

Provide an MCP server to enable reverse debugging with rr, improving control and insight during program execution analysis.

🏎️ DRS: Debugging at the speed of F1. An AI-powered Rovo Agent that instantly links Jira incidents to buggy Bitbucket commits.