Havuz

智能终端命令助手 — 用自然语言生成 Shell 命令，支持 OpenAI/Claude/Gemini/Ollama 等多后端

Agent-first X/Twitter client in Go — JSON envelope per command, multi-account, cookie-safe anti-detection for autonomous agents

Claude Web 服务，提供 Web UI 与 REST API 服务. Claude Web service providing a Web UI and REST API.

Search and download torrents from your terminal, or ask your coding agent to.

Run AI coding agents in parallel on one git repo and safely auto-merge their work — only changes that build and pass tests land. On top of p

CLI toolkit for Dynamics 365 Finance & Operations X++ development. Indexes AOT metadata, scaffolds objects, and wires up AI agents via a sta

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

Image generation CLI that reuses your Codex (ChatGPT) login.

The AI Runtime for Kubernetes

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

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

Multi-provider AI agent CLI written in Rust

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

A full-featured TUI MeshCore client for your terminal

Watch anime, movies, TV series and YouTube from your terminal with mpv. Search, switch sources, resume playback and queue offline downloads.

Universal local LLM runtime. Drop-in Ollama replacement with HuggingFace integration, pipelines, structured output. Free & open source.

Python CLI for managing Facebook & Instagram ads via the Meta Marketing API. Built for AI agents (Claude Code) and scripts, with safe dry-ru

Deterministic bytecode VM for agent execution - verified images, snapshots and a hash-chained replay journal

The lazygit for AI coding agents: skills, sessions, usage, providers and hooks for Claude Code, Codex, Gemini CLI, OpenCode, Pi, Crush and H

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)

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

Grepleaks — your AI pentest environment. An AI pentest agent that lives in your terminal.

High-performance OpenAI & Anthropic compatible API gateway for Qwen with multi-account rotation, interactive TUI dashboard, and resilient to

Turn any MCP server into a CLI in one command.

A fast, opinionated linter, validator, and formatter for Mapbox GL and MapLibre GL style JSON files.

An open-source AI assistant for work and everyday life. Remembers context and helps you get things done. Local-first, on a computer you choo

Drive a real browser from the command line and from MCP. Stable element refs, zero dependencies.

A Rojo superset that keeps each feature's server and client code in one folder.

Forge Agent is a free, autonomous AI coding agent that requires no API key or subscription. It uses browser automation to communicate with a

開源的輕量專案溝通、任務追蹤系統，也讓 AI 互相交接：客戶開單，團隊與 AI Agent 處理到結案 / Lightweight open-source project communication and task tracking, with AI agent handoff

Spettro is a terminal coding assistant built in Go. It automates planning, coding, and testing with multi-agent workflows, model selection,

Write commit messages, grep by meaning, turn English into shell — small composable CLI tools backed by an LLM. Local by default (no API key)

The last harness you'll ever need.

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

Hillclimbing on verifiable rewards. Use Claude Code and Codex to autonomously search for python programs that optimize a score you define. 🏔

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and

Lydia is a local AI coding agent for the terminal. It reads and edits your code, runs commands, and drives git through a local Ollama model.

Terminal-native agent for clinical workflows — prior auth, coding audit, and documentation, with reviewable output

A mobile control plane for persistent AI agents over Tailscale, Mosh, Herdr and ntfy.

WeChat 4.x local WCDB key bootstrap CLI for wx-mcp

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

Windows command-line and desktop toolkit for Xbox 360 RGH/JTAG development, diagnostics, file management, and reverse engineering.

Desktop & phone notifications for AI coding agents (Claude Code, Codex, Gemini CLI, Cursor). Native VS Code support. Toast + ntfy push. Zero

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Reverse-engineered design documents for Anthropic Claude Code CLI - implementation-ready specifications

Checks coding agents' edits as they work by enforcing mechanical guardrails for clean code.

Evidence-driven stock market analysis CLI for A/HK/US/JP/KR stocks, funds, and portfolios.

CLI tool for extracting files from damaged, corrupted, or encrypted APFS disk images. Written in C11, macOS-first (Linux supported). Handles

Reissue an API key with one command and update it everywhere it is used (1Password + templates)

A fancy NVIDIA GPU monitor for the terminal. One Python file, no dependencies.