Havuz

Terminal-native AI coding assistant for real repositories. Inspect code, edit files, run tests, and verify changes from the CLI.

Embedded agents your customers use to automate work, build views, and connect their tools.

🧬 devtools for agents

Cheaper and better Greptile alternative runs on your own github actions.

Open-source universal AWS resource browser for MiniStack, Floci, LocalStack, Moto, and real AWS

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

AI Engineering Runtime for Professional Developers — terminal coding agent with IOSM methodology, MCP, checkpoints, orchestration, and exten

Tooling to visualize React Server Components vs Client Components boundaries in Next.js App Router

Automated Discord Quest Reward Collector Tool 2026

Git-native truth docs for AI-assisted codebases, keeping branch-scoped documentation aligned with code so changes stay visible, reviewable,

Analyze your Claude Code context window, detect wasted tokens, and get pasteable fix commands. Zero API calls

A local dashboard to manage AI coding agent skills — sync, install, and organize skills across OpenClaw, Cursor, Claude Code, and more.

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into

React Native's internals — Fabric, Yoga, Hermes — as a universal native rendering layer. Drive the real iOS/Android stack from several UI fr

Dashboard for monitoring and managing Hermes agent sessions, tool usage, and activity in real-time

Free, native MongoDB GUI with the power of paid tools — every auth mode, TLS/SSH/proxy, aggregation + explain plans, bulk edit, schema analy

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compile

The all-in-one debugging toolkit for React Native.

Understand Software. Architecture intelligence + client-side security for any web app, right in your browser. Local-first Chrome (MV3) exten

Hide Your TailwindCSS 👀

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

A zero-dependency WCAG 2.2 accessibility audit engine, written from the W3C specifications. Runs entirely in the browser and reports what it

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

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

⌘-click an element in your running app, say what to change, and Claude, Codex, Cursor or another AI agent opens with the exact file and line

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

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

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

Control Kiro CLI from Telegram over the Agent Client Protocol (ACP): switch projects, resume & attach to live coding sessions, streamed resp

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

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

A Symfony Web Profiler-inspired toolkit for NestJS — profile every request with a rich panel UI. Powered & maintained by Eleven Labs.

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

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

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

Patches fetch/XHR to catch duplicate and needlessly sequential network requests during development, with call-site console warnings.

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-

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

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.

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

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

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