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

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

Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦

Local-first AI agent workbench for long-running projects: background work, built-in memory (no Docker), six web search services, MCP. macOS,

An always-on local autonomous agent

你是否厌倦了 Codex 多个账号之间来回切换？本地账号管理、官方登录、额度查询、快速切换与跨设备导入导出。Local Codex account profiles, login, usage, switching, and export/import.

Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.

Status bar for Codex CLI and Claude Code: context, 5h/weekly quota with reset times, tokens.

Open-source Desktop coding agent that's friendly to non-developers and puts you in control of everything, down to its tools.

Switch AI coding tools between your accounts. App and command line for macOS, Windows and Linux.

A polished terminal UI (TUI) for the pi AI coding agent — real-time chat, multi-provider LLMs, tools and sessions. Built with Go and Bubble

Gobstopper is an intelligent compaction proxy for Claude Code and Codex. It compacts more often, keeps history local, and cut tokens 29% on

一键诊断并修复 Codex / ChatGPT 桌面版「正在重新连接 1/5 → 5/5」| The Codex Rust backend ignores the Windows system proxy unless respect_system_proxy = true

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

a terminal coding harness

Turn CNB cloud-workspace in-network AI into production OpenAI & Anthropic (Claude Code) APIs. Zero deps, v5.2 self-healing HA, quota CLI.

Mercury CLI: multiple AI coding sessions in one terminal. Mix and match provider and locally hosted models, spawn cross-company agents & wor

OpenAI Privacy hackathon - Paris, 🏆 winning project

Model router for AI coding agents: routes routine work to cheaper models with routing rules, 8 subagents, hooks and a CLI runner

Keep it simple, stupid. A highly performant agent harness inspired by Pi, built in Rust.

Open coding agent that matches the best at lower cost: any model, sandboxed, scriptable, embeddable. Engine of Murage.

Community troubleshooting knowledge layer for OpenAI Codex

A repo investigator for Claude Code and Codex. Offload codebase investigation and get up to 2.7× as much work from the same limits.

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with

Generate images from local Grok, Antigravity, Cursor, or Codex logins, with official API keys as fallback.

Run Claude Code, Codex and other agent CLIs as one crew across your Mac, Linux box and Raspberry Pi. Self-hosted P2P mesh, CLI and web conso

The AI agent with a memory that lives on your machine and answers the phone.

Andromity - A terminal AI coding agent. Autonomous by choice, gated by trust.

Tiny Rust port of Pi — a ~4 MB statically-linked coding agent CLI for old/low-resource Linux boxes. OpenAI + Anthropic providers, streaming

The durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line

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

One hotkey to ask any AI on Mac. Open-source menu bar assistant: press ⌥Space to ask with your own API key (OpenAI, Claude, any OpenAI-compa

Переписывает промпт под правила модели, где вы работаете (Claude Opus 5.5, Fable 5.1, GPT-6 Astra/Sol/Luna, Codex), и подсказывает, на каком

Local-first usage & cost meter for AI coding agents: Claude Code, Codex, Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI. No ac

Rust AI Agent framework with MCP support, extensible tools, streaming & multi-agent orchestration

Opt-in dual-agent workflow: Claude Code plans and reviews, Codex implements, deterministic gates verify, and you decide what merges.

Diff your AI agent's behavior between two runs. See exactly which tool calls, args, costs and outputs changed when you swap models or edit p

Interactive patcher for the Claude Code native binary. Live inline thinking, detailed tool calls, subagent model overrides, custom branding

Run Claude Code on any LLM provider without losing your setup, local-first proxy with verified profiles, OAuth device-flow login, failover,

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, c

Run Claude Code and Codex across multiple subscription accounts. A local Rust proxy that sends each request to the account with quota left,

把本机 Codex 工作记录生成可分享的 AI 打工小票：一行命令、完全本地、隐私优先、中英双语、主题切换，并支持扫码导入微信小程序。

Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI a

The AI Runtime for Kubernetes

Token-efficiency linter for LLM prompts and payloads

Private, provider-neutral context compression for LLMs. Reversibly compress schemas and logs inside your perimeter with zero third-party cal

Codex Security, kod depolarındaki güvenlik açıklarını taramak, doğrulamak ve düzeltme önerileri sunmak için CLI ve TypeScript SDK sağlar.

Neden yükseliyor · 76 günlük yaşına karşın yüksek yıldız sayısı ve son 28 gündeki 188 commit ile 20 farklı yazar, belirgin ilgi ve aktif geliştirme gösteriyor; OpenAI markası da görünürlüğüne katkıda bulunabilir. Bu veriler tek başına tarama kalitesini veya üretim ortamında benimsenmeyi kanıtlamaz.

Track and rotate your Claude & Codex usage across accounts from one live dashboard — read live, never spending a token.