Havuz

AI code review with DeepSeek: headless PR review automation that verifies PR descriptions claim-by-claim against real code, checks docs agai

Hide Your TailwindCSS 👀

agent-bridge

Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories

A tiny, filesystem-backed S3-compatible server for local development and testing.

Live DevTools for your running React + TanStack app — driven from the terminal by your AI agent, through one CLI

A lightweight Laravel queue monitoring package that tracks job lifecycle (processing, success, failure) across any queue driver. It provides

OSS license watchdog. Monitors GitHub repos you depend on and alerts you when a license changes, explaining exactly what you can no longer d

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

🚀 Kill the Junior AI Era. 🤖 Level up your AI code to Principal standards. No more sloppy lines or junior mistakes. Automated ESLint ✨ TypeSc

Generate project-tailored AI assistant rules & skills (CLAUDE.md, .cursorrules, Copilot instructions, AGENTS.md) in under two minutes. Works

Semantic shell command safety classifier — AST-based risk scoring for AI coding agents

Everything the native EventSource API is missing — typed events, auth headers, reconnect, and single-tab coordination.

Interactive 3D Git history visualizer & time-travel explorer with AI-powered codebase lore

A lightweight, zero-trust CLI tool built in Python to automate, encrypt, and stream database backups directly to multi-cloud storage.

Your coding agent gaslights you. GODKILLER doesn't. Disk gates > vibes. claim_done only after verify.

Pixel-precise DOM inspector that turns any element into a ready-to-run AI coding prompt. Works with Claude Code, Cursor, Codex. macOS native

Give Vercel AI SDK agents a real persistent filesystem with Amazon S3 Files.

High-performance Rust token compression engine for LLM inputs. Plugin-based, 50–95% token savings, AI-export diagnostics, CLI / Server / IDE

What your AI coding agents actually cost — by task, branch, model and file. Runs locally, dashboard on 127.0.0.1:4976, no telemetry.

A lightweight Rust process supervisor for local stacks, homelabs, and small servers.

Terminal UI for Tilt.dev, inspired by lazygit

GitDeclutter — safely analyze and clean stale local Git branches. Classifies branches as SAFE, REVIEW, KEEP or PROTECTED.

Tends your codebase while you're away. An always-on AI engineer that reviews your logs, implements your tickets and keeps your pull requests

Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by

Git repository activity at a glance. Contributors, heatmap, trends, branch comparison and changelog. Zero dependencies.

Local-first Python CLI for safer log sharing: redact secrets, tokens, emails, and local paths before posting to GitHub issues, tickets, or A

MCP server for AWS infrastructure analysis — DynamoDB, Lambda, SQS, SNS, S3, API Gateway, PostgreSQL, MySQL, MongoDB, Kafka & IaC drift. Wor

A Git-native dependency admission controller. Evaluates trust signals on every dependency change and blocks commits or builds when packages

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everythi

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

📱 Simulateur mobile local (iPhone/Android/iPad) pour tester tes apps web dans le navigateur, sans installation. Open-source, vanilla JS + PH

Give AI coding agents product, spec, task, QA, and release workflows in one command.

Claude/Grokbot plugin and scripts: long-running controller pattern to chunk and delegate code work to cli-agents, with embedded adversarial

Back up your dev environment — language runtimes & global CLI tools — and restore it on a new machine. Backups live in your own GitHub repo.

Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approv

AI-powered codebase architecture visualizer for exploring modules, dependencies, dead code, impact analysis, and project health in real tim

Chrome extension (MV3) that scans live Elementor pages and reconstructs full section/widget structure into an import-ready JSON template — n

The Search Engineer's Toolkit — open source CLI tools for Elasticsearch, OpenSearch

One-command Cloudflare Tunnel Zero Trust CLI

⚡ Adaptive multi-model LLM router — 80+ providers, Jev System One single-pass routing (model=jev-auto), pheromone-trail failover, parallel e

Fix the Google Antigravity 2.0 bug that splits one project into duplicate numbered Projects-panel entries (MyApp, MyApp 2, MyApp 3...). Scan

EasyQueue is a desktop application for inspecting, publishing, and managing messages across multiple message brokers from a single interface

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI wo

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-

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

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.