Havuz

Open-source, local-first AI coding agent. Build, share, and install skills. Runs on your machine. Your keys, your data. No cloud. No subsc

A fast, keyboard-driven TUI API client & webhook inspector. No cloud, no Electron, 100% local-first.

Developer tools for humans and agents: route work to the right AI coding agent, merge multi-vendor reviews into one gate, pin the skills and

Your team's coding agents warn each other before they edit the same file. Claude Code, Codex, Cursor and 17 more.

TypeScript toolkit for Windows x64 native systems programming, memory manipulation, and process instrumentation.

herdr for tmux: see which AI coding agent needs you and jump there in one key. herdr's detection engine for 22 agents, inside the tmux you a

High-performance full-text search across PDFs, Office documents, ZIP archives, email, media metadata and GGUF/LLM model files. ripgrep-compa

Git remembers what changed. cogit remembers why. A Claude Code plugin that records every message you send as a thought commit and links your

Finds the corrections you keep repeating to Claude Code and turns them into evidence-backed CLAUDE.md rules. Local CLI, no LLM by default, p

A machine-wide counting semaphore for heavy commands: N slots shared by every checkout and agent on one machine

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

Review what your coding agent changed, without leaving Rex. Think herdr-reviewr, but for Rex.

The context optimizer for AI engineers. Stop paying the context tax. 183k → 21k tokens before your AI assistant ever reads your repo.

Keep an eye on your AI coding agents: a live browser view of your agents, and CLI-based mail for them to collaborate on Tasks.

Your agent finally sees the Compose UI it builds. Jetpack Compose and Compose Multiplatform Previews in your browser, redrawn a second after

Agentic coding, in your control

Anything to API (万物皆可2API): put an AI agent, a script, or even yourself behind an OpenAI-compatible API

Know the risk of merging a pull request, and where it lives. Free, open-source CLI and GitHub Action: after your AI review, farol shows the

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

Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan

Cut your AI coding agent's token bill, locally: Claude Code, Codex, Cursor, Copilot. #1 on THOL, 39% cheaper on long sessions.

A terminal dashboard your coding agent sets up: PRs, Jira, calendar and anything else, with Plugins in any language.

Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents r

Run coding agents as a cluster: one repository, N agents, one worktree each

Git worktrees that share files through copy-on-write clones (APFS, XFS, btrfs). A git subcommand and a Rust crate

One command. Any URL. Cloned, reverse-engineered, running.

🧠 Persistent local-first memory for AI coding agents — MCP server + CLI for Claude Code & Cursor. SQLite FTS5, secret redaction, project iso

🏛️ Autonomous Multi-Agent CLI Orchestrator — Bring Claude Code, OpenAI Codex, Cursor Agent, xAI Grok & Google Antigravity into one terminal

MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers i

Agent 的 Ctrl+Z：一键精准撤销/重做。Ctrl+Z for Agent: precise undo & redo in one step. Works inside Claude Code, Codex, Gemini CLI and Cursor CLI.

Print a store receipt for your AI coding: tokens, what they'd cost at API prices, and how many times the agent said "You're absolutely right

Run Claude Code, Codex and Pi agents toward goals the daemon verifies itself. Give each agent a role and a goal with a completion check; Dud

Websites, ready for AI. Turn website tasks into verified CLI and MCP actions, with a local dashboard and 20 languages.

Simulator-free, headless SwiftUI checks for AI coding agents: render screens as accessibility trees and hot-reload views in ~2 s, without th

An open standard for agent-native software requirements.

nsq — run several AI coding agents in your terminal and stop babysitting them. Open-source CLI by NeuroSquad.

Telegram inside Claude Code: read chats and channels in a pane, get AI summaries of unread posts. No API key, no bot.

Scaffold production-ready apps with Next.js, TanStack Start, or React + Vite and a separate Hono or FastAPI API. Choose modules for auth, st

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until a

Phone ↔ PC file transfer from the terminal. Run npx chegou, scan the QR, done.

Make messy Linux command output readable. Formats git, systemctl, journalctl, ps, ip, ss, lsof and more. Single Go binary, stdlib only.

Turn your app icon into a blueprint version, like Xcode's icon, for your debug builds

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

Group chat for humans and coding agents. Mention @claude, @codex, @cursor or @gemini in a channel: the agent runs on your machine with your

Plain Git versioning for the files that are yours, not the project's: notes, scripts, skills, and agent instructions, all hidden from the pr

⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on No

面向 AI 编程智能体的任务包工作流工具，用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)

Live step-by-step progress bar for long Claude Code sessions, in the terminal and the Desktop app

Review code changes by what they do, and learn the concepts behind them.

Quiet tmux status for Claude Code, Codex, opencode & pi — shows nothing while agents work, a small marker when one needs you. No dashboard,