Havuz

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

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

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

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.

Community registry of LLM serving-path traps that produce confidently wrong measurements: templates, tool parsers, reasoning fields, quant k

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

Autonomous, headless Android debugger designed for AI coding agents. Inspect runtime memory, set breakpoints, and debug live apps.

An open-source collection of embedded development and debugging skills for Claude Code, Copilot, TRAE, and other AI coding assistants that s

A command watcher that commits when you fix errors

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.

Run Windows and Linux programs on Windows, Linux and Android. A user-mode NT and Linux kernel emulator with WHP/KVM acceleration.

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

Visual Docker dashboard with a 3D dependency graph, live metrics, logs, terminal, and container actions

iOS dynamic library MCP for agents

One command to explain your Python environment, trace imports, and detect shadows.

Patching the Secure Kernel to enable debugging of VTL 1 Isolated User Mode

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

MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems

Visualize and analyze Laravel's complete request lifecycle with detailed execution timelines and performance insights.

Universal Aim Assistant and Developer Tools Suite 2026

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

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

Illusion Game Trainer Hub: Open-Source Cheat Tools and Mods 2026

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

Best Illusion Game Modding Toolkit 2026

Capture Kubernetes cluster state to a portable archive and replay it through a mock API server — use kubectl against a customer's environmen

Session replay for Laravel, built on rrweb: a recorder with privacy defaults, token-signed ingest, recordings on your own disk and database,

lightweight cross-platform memory visualizer tool

PHP debug engine that works without extensions AST instrumentation + file-based IPC. Powers DDLess.

An in-app developer console for Flutter: inspect HTTP, WebSocket & gRPC traffic, monitor logs, database, memory leaks and FPS in real time,

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

Unofficial pre-submission compliance and runtime checker for Yandex Games

Slang shader line previews for nvim

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

Catch silent failures in AI agents before your users do

Inspect ASP.NET Core HTTP traffic with a built-in dashboard and compare traces across environments.

In-app debugging overlay for Compose Multiplatform: inspect network traffic, database contents, background work, logs and crashes from insid

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

Claude Code skill that finds and rates other instances of a bug you just fixed, then presents options to fix them after explicit user approv

Cross-platform Modbus toolkit (PySide6): master client with register table, polling, live graphs, alarms and bus scanner; device simulator (

Developer tools for inspecting and debugging GPUI applications

Fable-inspired verification-first workflow skill for Codex

Your coding friend in the terminal.

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

Gronex — Machine coding, LLD, repository-based, FDE, AI-researcher & production-incident interview problems. Solve each in a real backend re

Quiet, risk-scaled engineering methods for Codex. Method as exponent, not machinery.

Find out exactly why an EIP-712 signature fails.

DeepSeek Harness plugin: 15 obra/superpowers engineering skills, bilingual descriptions, per-skill toggles | DeepSeek Harness 插件：15 个 obra/s

Self-hosted webhook inspector. Single binary, SQLite, no external dependencies.

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