Havuz

Your agent’s trace says “success” but the answer is wrong. Tracedown finds the step that caused it and replays the run with a fix.

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

Wireshark for MCP. A transparent proxy between your AI client and MCP server. Watch every call live in your terminal, fail CI on what it fin

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Jeview, Jev (TypeSafe System One) API çağrılarını yerelde kaydedip canlı haritada görselleştiren bir gateway ve geliştirici aracıdır.

Neden yükseliyor · Repo 6 günde 56 yıldız almış; bu erken dönemde dikkat çektiğini gösteriyor, ancak yıldızlar kullanım veya kalite kanıtı değil. Son 28 günde 15 commit ve 1 farklı yazar bilgisi geliştirme hareketliliğine işaret etse de katkı tabanı tek kişilik. İlginin kesin nedeni verilerden anlaşılamıyor.

A host-side, scriptable command-line terminal for Segger-RTT; Also the AI-ready command line for embedded validation.

Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents: inspect causal runs, catch wrong tool paths in CI, and share s

Debug Anything: observe any running process, container or pod from your AI agent. strace, py-spy, perf, lsof, tcpdump, gdb/lldb and heap sna

iOS dynamic library MCP for agents

TCP-enhanced fork of Cheat Engine MCP Bridge. Connect Cursor, Copilot and Claude AI directly to local or remote Cheat Engine via TCP. Automa

Verify what your Claude Code agent actually did. Rashomon keeps an independent record of every tool call, subagent, failed command, and flag

🚇 A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Pr

MCP development, debugging, migration, and verification for coding agents, backed by an engineering guide and executable lab.

melonDS fork with full MCP (Model Context Protocol) integration: agent-controlled emulation, instruction-level debugging (breakpoints/watchp

8 character-driven AI coding agent skills for Codex: debugging, code review, regression testing, and release checks. Weird, but employed. In

Turn noisy command output into a short, actionable first pass for coding agents.

Let AI agents play, observe, and debug games in emulators through MCP.

Chromium (Chrome/Edge) DevTools panel for debugging SSE / EventSource / NDJSON streaming responses. Inspect, filter, search, and export stre

Standalone observability dashboard and developer playground for the Laravel AI SDK. Zero build steps. Telescope for your AI agents.

Fable-inspired verification-first workflow skill for Codex

Give AI hands to touch silicon — an MCP server for SEGGER J-Link, OpenOCD and Black Magic probes. Flash, halt, step, stream RTT logs and dec

デバッグ能力を「鍛える」と「測る」を1つにしたBtoB向けの仕組み。AIは答えではなく段階的な問いを返し、業務を止めずに技術力が育つ。到達度・正答率・成長率を5軸で可視化し、人事評価の客観的な根拠として使える。

Catch silent failures in AI agents before your users do

Antigravity Observability Console & Wire-Tap Module

Local monitor for Claude Code API traffic, logs, prompts, and tools

Your coding friend in the terminal.

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g

Open-source MCP server for AI-autonomous Godot game development. Deterministic playtesting, multiplayer testing, DAP debugging, LSP, token-e

Stack traces that tell the tale — a Logback appender that turns Java errors into AI-ready reports

Logic-first AI code review via semi-formal execution tracing (Premises → Trace → Divergence → Trigger → Remedy). Catches behavioral bugs, ty

An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.

Visual debugging, execution traces, and observability for AI agents.

MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --l

Roslyn-enriched C# exception telemetry for Godot Engine, exposed over MCP

Plugin-first AI terminal workspace for Codex and Claude Code with planning, CI/CD debugging, reusable agents, skills, TODOs, and MCP tool in

Reviewable capability layer for coding agents: portable skills, workflow patterns, verification gates, token-efficient execution, and bounde

Counterfactual replay and causal attribution over LLM-agent trajectories: find which step actually caused a failure by intervening on it.

MCP server that lets AI agents (Claude, Cursor) debug your .NET / ASP.NET Core app

Husk-AI runs your AI agents inside (or alongside) a local Studio and shows you — in real time — what they think, where they fail, and how a

AI-assisted reverse engineering orchestration platform for IDA Pro and x64dbg with live synchronization and MCP agent workflows.

The debugger for AI agents — capture every run, inspect every decision, pause and inject live, fork from any step.