Havuz

One hub for every AI coding agent. Unified configuration management for 22+ assistants.

Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom propertie

Open-source Canva alternative you can self-host: graphics, slides, video, whiteboards and docs. AGPL-3.0.

An engineering team in a box for Claude Code — 12 specialized agents, 15 automation hooks, and the P7/P9/P10 methodology.

Turns any OpenAPI/Swagger API into an CLI with set of commands. One CLI command per endpoint.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history,

Asks what to optimise and how to measure it, then runs experiments on its own branch.

Keyty - modern open-source keyboard and mouse visualizer for macOS

Local-first AI coding quotas and ship status, on your menu bar, iPhone, Watch and an ESP32 desk display.

Self-hosted email sending platform built on Cloudflare Email Sending — REST API, admin UI, templates, domain management, scoped API keys, al

A comprehensive statusline dashboard for Claude Code — session info, quota bars, agent tracker, MCP health, message history, and more.

Install, manage, and share skills across every major coding agent — Claude Code, Cursor, Copilot, and more.

The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestrat

Kane CLI by TestMu AI (Formerly LambdaTest)

Spotify player for the terminal. With reactive themes.

Production-grade Playwright + TypeScript Scaffold for Agentic Testing. Harness for all major AI coding agents baked in.

Ant Design on your command line. Query component knowledge, analyze project usage, and guide migrations — fully offline.

Run multiple Claude Code and Codex sessions in parallel — a browser terminal grid that shows which agent needs you. Local, tmux-backed, MIT.

find and download fonts from the terminal

Guided private-tracker upload preparation: metadata, dupe checks, screenshots, descriptions, submission, and torrent-client integration.

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation,

A unified agent memory workspace for human and agent | 一个统一的agent记忆工作空间

Catch undocumented, unused, and drifting environment variables in your repo

⚡ CLI toolkit for Google Flow — Nano Banana Pro images, Omni Flash videos, MCP v2 & OpenAI API.

Network traffic visualization tool

Privacy-aware trajectory viewer for local Codex task logs

MCP server for 1С:Enterprise — AI assistant sees your configuration and generates accurate BSL code. One binary, zero dependencies, 19 tools

Command-line tool for Meegle (Lark Project). Manage work items, schedules, and data from your terminal — no browser needed.

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

README-first, evidence-backed analysis for understanding public GitHub repositories before adoption.

Automated quality checks that nudge AI coding agents toward better habits

50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster through natural lang

MCP server for the complete Zabbix API - 237 tools, multi-server, OAuth 2.1 + bearer auth, PDF reports, systemd ready. Works with ChatGPT, C

Local, zero-dependency dashboard for Claude Code: live token usage and context, lost-session recovery, full-text search, and approve tool ca

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Turn any CAE files into structured text an agent can use

Open source alternative for frame.io

Persistent local memory layer for AI. ArcRift uses a extension and a native MCP server to sync context and decisions from your browser chats

JeecgBoot Skills — AI 驱动 · 一句话生成全套工件! 在 Claude Code 中，用一句话生成 代码 · 表单 · 流程 · 报表 · 图表 · 大屏 · 仪表盘。 覆盖 JeecgBoot 低代码平台 与 JimuReport 积木报表 两大产品的企业

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无

Claude Code statusline and rate limit tracker with pace-aware quota monitoring. Pure Bash + jq, single file.

Cross-platform environment manager for Antigravity CLI, Manager & IDE — eligibility patching on Windows, Linux and macOS (x64/ARM64), plus m

AI-native, keyboard-first Git desktop client combining GitHub Desktop's ease with advanced Git, PR, issue, discussion, Actions, and notifica

The open standard for runtime agent control — declarative hooks, policy enforcement, and observability across AI agent frameworks.

Maintainer-governed agent for evidence-backed open-source contribution proposals

Open-source, self-hosted AI language learning platform with local or cloud LLMs, CEFR study plans, an AI tutor, voice conversations, flashca

Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Studio, MLX, llama.cpp) or cloud,

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with