Havuz

Find out whether your Next.js app actually leaks memory - how much, on which route, and whose fault it is.

MCP server for Claude Desktop and other Model Context Protocol clients — sandboxed filesystem access (read/write/edit/search) plus Dev Mode-

Contract intelligence, inspection, interface analysis, compatibility, deployment verification, and reproducibility tooling for Stellar and S

An AI-powered Git pre-commit/pre-push security gate

Remove Claude/AI attribution from a GitHub repo in one command clean commit history, force-push, and refresh the Contributors graph so @clau

Compare design directions inside existing apps. Try many variations of a component, feature, page or user-flow quickly. Try all your ideas.

Kibana's DevTools in a terminal: query Elasticsearch or OpenSearch when Kibana isn't there, or is down. One Go binary for Linux, Windows and

Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.

Static security & correctness linter for Payload CMS. Zero-config, deterministic, ts-morph-based. Catches access-control gaps, unsafe Local

Vue DevTools for Rspack and Rsbuild - full feature parity with the Vite plugin

Son of Anton, reimagined as a web app — Node + WebSocket + node-pty + xterm.js, zero Electron.

Fast, local-first Git desktop client, code intelligence suite, and task workspace built with Rust (Tauri 2) and Svelte 5. 100% on-device, ze

The skill composer for AI agents — merge skills from Anthropic, OpenAI, GitHub Copilot, Microsoft, Google + 8 more ecosystems with AI-powere

Point at any part of your running app, describe the change, and Lasso edits the real source file — not the DOM. Works with Vite and Next.js.

Capture browser and server logs in one correlated place - and let your AI agent read them over MCP

Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and befo

Hear a short spoken summary after your coding agent answers. Free to install - no API keys, no subscription, no cloud TTS.

Find gaps between .env, .env.example, shell variables, and Python code.

npkill for Next.js — nuke bloated .next folders and reinstall a fresh instance. Monorepo & pnpm aware.

Browser automation for AI agents in your real, logged-in Chrome. You watch every action and can veto any tab. Chrome extension + zero-depend

Self-hosted Laravel Flight recorder with request tracing, SQL intelligence, queues, Redis and server health — no telemetry database.

A docker compose for Apple's native container runtime — run your compose.yaml on Apple silicon, no Docker daemon.

Turn your Claude Code / Codex subscription into a Feishu agent your whole team can @

Spec-driven development skills plugin for Claude Code and Codex: 16 tn: skills for spec, implementation, verification, release, and archive.

Local dashboard for Dapr developers: live view of apps, sidecars, workflows, actors, pub/sub and logs from dapr run, .NET Aspire, Docker Com

The brain is a git repo. Memories are markdown files with YAML front-matter, committed like any other file. Git history is the audit tra

Chrome DevTools for .NET MAUI. Inspect and live-edit the visual tree from a browser panel, write the edits back into your XAML, mock and int

⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel,

Terminal side pane for Claude Code that shows a session's agents as a live tree. Stop a running sub-agent, send it new instructions mid-task

Spine — governed, provenance-grounded autonomous software delivery (installs as agent-orchestrator).

Local-first tool to visualize and analyze Claude Code, Cursor, Pi & OpenCode sessions — context tokens, LLM insights, governance artifacts.

Auto-complete all 5 Discord Quest types in one run - game, video, stream, activity, achievement. Built-in dashboard, resilient module detect

Clide — AI SSH terminal desktop app with Claude Code IDE & MCP integration. Tauri · Windows/macOS/Linux

AI Agent watcher that helps developers/Agencies build from idea to launch while reducing token usage, preserving context,using 140 skills, a

Go LLM Execution Model — Go 原生 AI 编程 Agent CLI。单二进制、三层记忆、YAML 权限规则，TUI 对齐 Claude Code / Codex。

The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.