Havuz

Answer a few multiple-choice questions. Your agent builds a finished website, checks it in a real browser at phone and desktop size, and put

ChatGPT Session ↔ 9 种主流认证格式 N×N 双向互转（auth.json / Cockpit / CPA / Sub2API / 9router / AxonHub / Codex-Manager / Codex Auth / Raw）· 11 种来源自动识别

Personal-memory-driven AI work twin that uses Codex to work inside real projects.

Code-quality skills by Max Kanat-Alexander.

Control your local Codex sessions remotely through Discord on your phone or browser.

Open-source Claude Code Desktop alternative. Use any provider/model. Web UI for Claude Code, Codex, Gemini CLI, OpenCode, Hermes.

A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No

制作统一漫画墨线风格的解释图与透明角色插图，用于概念、流程、比较和文章配图。

Codex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

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

elastic inference for your agentic workloads, on your terms

Watch, approve and steer your coding agents from your phone.

Private local meeting rooms where Codex, Claude Code, and other agents collaborate live.

Local-first AI memory you can see, edit, and override — portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools.

Headless product design for AI coding agents, backed by a transactional product graph | Design how it works, verify what you ship.

Agent skills that turn docs/ into an LLM-maintained wiki and task tracker. Obsidian-friendly. Works with Claude Code, Codex and Copilot CLI.

An open-source workspace for coding agents, running on your own machine. More work. Less AI waste. Same subscriptions.

OpenCode zen/go to OpenAI Codex/Anthropic Claude Code API proxy

💡 Turn experience into repeatable execution.

Terminal Director. One lightweight app, eight features, your whole dev workflow in a single window.

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

AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQLite.

UI/UX skill for Claude Code, Codex and Cursor. Polished, plain interfaces with no AI slop. Includes a zero-dependency slop checker.

Your app is guilty until proven secure: an agent skill whose /hack-me breaks into your own running app, proves each bug with a real request,

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

macOS 原生 AI 额度监控与用量分析工具，实时监控 Codex、Claude Code、Cursor、Antigravity 剩余用量与本地 Token 消耗和费用。 Native macOS menu bar app to monitor quotas, reset co

Metrik 可以集中查看本机多个 Agent 的配额余量和 Token 消耗，目前支持 ChatGPT、Claude、GLM、Kimi 等主流 AI 服务。

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

A terminal interface for Nanocodex

A desktop app for running coding agents side by side in project-based terminal sessions.

Open-source canvas for orchestrating Claude Code, Codex, and other CLI agents. Run agents in parallel, delegate tasks, and let AI build reus

Full-configuration CLI for Codex Micro and Work Louder Input: profiles, layers, keymaps, actions, provider handoff, verified apply, and roll

Multi-Agent AI Task Orchestrator 2026

Claude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT v

Self-evolving browser automation for Codex, Claude Code, and Cursor—learn reusable site knowledge and safely replay verified routines with a

Plan through one coordinator conversation, run coding agents on focused tasks, and handle questions and approvals in one Inbox.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, c

A local privacy firewall for AI agents: masks secrets and personal data before a request leaves your machine and restores them in the answer

A perch for your agent projects — jump back into recent Claude Code / Codex projects, resume the last session, one keystroke away

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

Free LLM gateway: 22 LLM providers, 178 enabled chat routes, 431 cataloged chat models; keyless start when available.

Polya Agent Skills for developing and programming apps with AI Agent, coding agent tools, and AI harness

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives you

One safe command (or a signed GUI) to set up Claude Code, Codex and a dev environment on macOS, Linux and Windows. Dry-run first, repeatable

A workflow harness that helps AI coding agents plan, review, test, and ship safer code.

Read what your agent wrote before you say LGTM. A fast TUI in Zig for reviewing code with vim motions.

An event-driven WebMCP watch-along for Codex and ChatGPT.

Curated developer tools, AST analyzers, and automated verification workflows.

Claude Code plugin: use ChatGPT (Codex), Cursor, OpenCode Zen, and Antigravity models inside one Claude Code session. Switch with /model, de