Havuz

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Your coding agents, working together as one team. Claude Code, Codex, Cursor and 13 more talk to each other, split the work on a shared boar

Thinking in the Human · Processing in the AI · Truth in the Documentation

Fast, tiny AI coding agent for the terminal, written in Rust. One small native binary for Apple Silicon Macs. Works with OpenAI, Anthropic a

AI code review that lands on the PR, not in your terminal — GitHub, GitLab, Bitbucket. Learns each repo's conventions: 1 review, 1 fix commi

Diagnose why commands work in your terminal but fail in an AI coding agent. Compare Windows/WSL execution contexts and generate redacted rep

Reusable, production-grade Lightning Web Components and Apex services: a generic server-side datatable, a modal framework, error/state handl

Open-source self-hosted web tool for evaluating Agent Skills with rubric scores, Deep Review, and improvement suggestions.

On-device shell command generator for macOS Tahoe. Uses Apple's 3B model with dynamic few-shot retrieval from 21k tldr examples.

A CLI that extracts the useful structure from source files: signatures, imports, types, variables, comments, and Markdown sections.

Extract structured knowledge from Cursor & Claude Code conversations into git-trackable Markdown files

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, the

Bedrock is a CLI tool that bootstraps AI-ready project configurations by generating standardized rules, skills, and project context tailored

A skill for Antigravity that delegates scoped work to Gemini CLI or Codex CLI worker agents — keeping the main context clean.

Local static analysis and baseline-governed CI checks for coding-agent instructions: AGENTS.md, CLAUDE.md, Cursor, Copilot, and Gemini.

A fast, native MongoDB GUI — built with Perry

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, ap

A light TablePlus alternative for PostgreSQL that your AI agents can use too, over MCP. macOS and Windows.

Local-first AI coding personality profiler, usage dashboard, and evidence-grounded roast.

Full AI-assisted coding platform for manual paste-and-apply workflows — no API keys, no subscriptions, no setup.

One engineering workflow for Claude Code, Codex, Droid, Pi and OpenCode, with a validator that refuses a record without its evidence. Alpha,

Claude Code plugin: see where your tokens go, audit your setup against the docs, and tune settings with an approved diff

Unofficial CLI for automating Apple Feedback Assistant workflows: prepare, submit, attach, and verify

Cut Claude Code costs with sourced levers -- prompt caching, model routing, Batch -- plus an installable skill, CLI tools, a cost calculator

Spec-Driven Development framework that enables humans and AI agents to build better software by giving them small, local instructions right

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

Free subdomains under makes.fyi / agentdomains.co, claimed from the CLI. A/AAAA/CNAME/TXT/NS records, auto-HTTPS proxy and forwarding for th

23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex deskto

Docker sandbox for the Claude Code CLI. Runs Claude against one project folder — including with --dangerously-skip-permissions — while your

Visual editing overlay for React apps — click any element, edit styles and text, source files update live. No AI. No cloud.

Deterministic, read-only Git evidence for coding agents and automation. Standard-library Python CLI.

CodeAuto is an intelligent programming assistant developed using Java, drawing inspiration from Claude Code and Minicode.

Kether-governed AI agent orchestration with Pi/MCP, isolated workers, LSP tools, and a portable Windows/WSL2 installer

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Pluggable role definitions for AI coding agents — one command turns Claude Code / Cursor / OpenCode / Codex into a specialized professional

Claude Code skill: Generate design.md, design-guidelines.md & design-components.md from any design references — images, PDFs, links, screens

A disposable copy of your production stack for every pull request: masked Postgres, contained third-party APIs, and agents that use your app

Real-time TUI diff viewer for AI coding agents

Claude Code usage recap with narrative. ccusage tells you the bill, ccstory tells the story.

Open-source AI assistant with voice control, browser automation, desktop overlay, and 109+ tools. Built with Python, Next.js, and Three.js.

Local, live code review for the AI age - read what the agent wrote and send feedback straight back

Generate test files for QA and automated testing, 31+ formats at any exact byte size, with ready-made presets, reusable recipes, and manifes

The animated diagram editor AI agents can draw on. Animated technical diagrams (architecture, sequence, BPMN, cloud icons) built by you and

Persistent project memory for AI coding agents — isolated workspaces per project, web dashboard to review what your agent remembers, team co

WorkBuddy Multi-Account Manager & Automated Check-in Toolkit (多账号轮换、全域工作区打通与自动化签到)

CapCut Pro for Windows — free professional video editor with AI auto captions, effects, keyframes, transitions and high-quality 4K export fo

A composable CLI project generator and build helper for GoFiber applications.

Sandboxed Python environments with the uv workflow. Registry-only installs, read-only dependencies, and deny-by-default networking. Local-fi

MCP-native code retrieval for AI agents — 84-88% fewer read tokens, BM25F + semantic search, AST chunks, session dedup

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.