* [Marketing Skills for Claude Code v2.11.0](https://github.com/coreyhaines31/marketingskills) – Collection of AI agent skills for conversion optimization, copywriting, SEO, analytics, and growth engineering.

* [ChatGPT Web for Codex v3.0.0](https://github.com/miuuyy/codex-chatgpt-web) – ChatGPT Web bridge that runs selectable ChatGPT tiers as native Codex models with full task context, images, streaming, and MCP tool access.

* [Cherry Studio v2.0.0](https://github.com/CherryHQ/cherry-studio) – Desktop client supporting multiple LLM providers, available on Windows, Mac, and Linux.

* [FanBox v2.14.0](https://github.com/alchaincyf/fanbox) – Local-first cockpit for vibe coding that lets you browse and preview files on one side while running a coding agent in an embedded terminal and seeing every change live.

* [Codex Router v0.5.0](https://github.com/duolahypercho/codex-router) – External-model router for the Codex App and CLI that merges provider models into Codex’s catalog via credential-isolated, guided OAuth/API setup with safe migration and rollback.

* [opencodex v2.33.0](https://github.com/lidge-jun/opencodex) – Lightweight local proxy that translates Codex Responses API into multiple LLM providers with full support for streaming, tools, reasoning tokens, and images.

* [Skills Manager v2.2.0](https://github.com/jiweiyeah/Skills-Manager) – Skills Manager is a desktop app that centrally manages and symlink-syncs AI coding assistant skills across multiple tools like Claude Code, Codex, and Opencode.

* [Copilot API Proxy v2.3.0](https://github.com/caozhiyuan/copilot-api) – Reverse-engineered server that exposes GitHub Copilot as OpenAI- and Anthropic-compatible APIs for tooling and model compatibility.

* [Paseo v0.5.0](https://github.com/getpaseo/paseo) – Run and manage coding agents on your machines from phone, desktop, web, and CLI.

* [Clawd on Desk v0.16.0](https://github.com/rullerzhou-afk/clawd-on-desk) – Desktop pet reacting to AI coding agent sessions in real time with animations for thinking, typing, juggling, permission prompts, and sleep.

* [hapi v0.29.0](https://github.com/tiann/hapi) – Local-first interface to run and remotely control AI coding sessions across devices

* [CPA Manager Plus v1.12.0](https://github.com/seakee/CPA-Manager-Plus) – Management panel and Docker-ready manager server providing SQLite-backed usage analytics, request monitoring, model pricing, quota views, and Codex inspection for CLI Proxy API.

* [Codex2API v2.8.0](https://github.com/james-6-23/codex2api) – Go + Gin backend with a React/Vite frontend providing an API for OpenAI Codex with PostgreSQL/Redis or SQLite support.

* [ModLens v3.14.0](https://github.com/liustack/modlens) – ModLens is a vision plugin that lets text-only chat models process pasted images and return structured evidence like transcripts, layout regions, and entity relations.

* [META\_KIM v3.0.0](https://github.com/KimYx0207/Meta_Kim) – Governance layer that coordinates AI coding assistants via an 8-stage workflow, contracts, gates, and memory to improve execution and learning.

* [codemap v4.4.0](https://github.com/JordanCoin/codemap) – Generates compact, token-efficient architectural maps of codebases to give LLMs instant context.

* [SOLO v1.0.0](https://github.com/solo-agent/solo) – Local-first workspace that coordinates humans and AI coding agents with channels, threaded conversations, task boards, and channel-scoped teams.

* [AIClient2APIA2 v3.4.0](https://github.com/justlovemaki/AIClient2API) – Proxy that unifies client-only LLM APIs into an OpenAI-compatible local interface and simulates model requests.

* [botmux v3.10.0](https://github.com/deepcoldy/botmux) – Bridge that routes Feishu/Lark chats to AI coding CLIs, spawning per-DM or per-topic live tmux sessions.

* [CLI Proxy API v7.2.119](https://github.com/router-for-me/CLIProxyAPI) – Proxy server providing OpenAI, Gemini, Claude, Codex, and Qwen compatible API interfaces for CLI models with multi-account support.

* [PenEcho v0.8.0](https://github.com/penecho/penecho) – A shared canvas that reads handwriting and diagrams with spatial context and generates editable AI answers beside the marks.

* [lnwjud v4.13.0](https://github.com/engasnm111/lnwjud) – Windows-first local AI-agent runtime and MCP gateway that exposes trusted capabilities through MCP for files, Git, processes, Windows automation, WSL, browser control, indexing, and observability.

* [codex-cli-nix v0.150.0](https://github.com/sadjow/codex-cli-nix) – Nix flake providing an always-up-to-date, native Rust OpenAI Codex CLI with hourly updates and multi-platform binary cache.

* [deja-vu v0.19.0](https://github.com/vshulcz/deja-vu) – Zero-dependency CLI memory layer that indexes Claude Code, Codex, and opencode session logs for fast search, agent recall, redaction, stats, and sync.

* [toSub2 v1.7.0](https://github.com/poxiao33/toSub2) – Protocol-based ChatGPT and Codex OAuth client that handles 2FA TOTP and generates sub2api import data from stored tokens.

* [codex-multi-auth v2.9.0](https://github.com/ndycode/codex-multi-auth) – Multi-account OAuth manager for the official Codex CLI with resilient routing, quota-aware rotation, and terminal-first diagnostics.

* [Dinotty v0.23.0](https://github.com/xichan96/dinotty) – Dinotty is a multi-device terminal server for AI coding agents, offering server-side VTE, session persistence, file browsing, web preview, and a plugin system.

* [repo-harness v0.17.0](https://github.com/Ancienttwo/repo-harness) – A CLI and hook system that turns Claude/Codex coding into a repeatable, repo-local workflow with resumable plans, checks, and review evidence.

* [Skills Hub v0.9.0](https://github.com/qufei1993/skills-hub) – Cross-platform Tauri and React app for installing, organizing, updating, and syncing Agent Skills across multiple AI coding tools’ skills directories.

* [Ouijit v1.7.0](https://github.com/ouijit/ouijit) – Git worktree-based task and terminal session manager integrating agent CLIs, lifecycle hooks, and VM sandboxing.

* [oc-codex-multi-auth v6.14.0](https://github.com/ndycode/oc-codex-multi-auth) – OpenCode plugin enabling ChatGPT Plus/Pro OAuth access, GPT-5/Codex model presets, multi-account rotation with failover, and guided setup.

* [VaneHub AI v1.0.0](https://github.com/cdavid817/vanehub-ai) – Desktop-first workspace that unifies AI coding agent CLIs and native HTTP agents in one React interface with clear runtime boundaries.

* [Stop That Shit 0.1.0](https://github.com/lennney/stop-that-shit) – Multi-platform hook and skill guard for AI coding agents, blocking unrequested hashes and checksums and preventing task-scope creep.

* [Codexia v0.48.0](https://github.com/milisp/codexia) – GUI and toolkit for managing Codex CLI projects, sessions, file-tree navigation, prompt notepad, git worktrees, file viewers, and usage analytics.

* [49 Agents IDE 0.4.0](https://github.com/alpbahadur/49Agents) – A 2D agentic IDE that unifies terminals, files, and multi-machine agent workflows in a zoomable canvas.

* [Codex Taskboard v1.1.2](https://github.com/chuspeeism/dashi-taskboard) – Codex Taskboard is a macOS-focused task management app with a local React frontend, HTTP API, and a CLI and skill integration for Codex/ChatGPT workflows.

* [Smithers v0.35.0](https://github.com/smithersai/smithers) – Durable AI orchestration framework for defining workflows as React components.

* [Alethe v1.6.0](https://github.com/Kc1t/alethe-agents) – Local-first desktop workspace that runs multiple coding agents and shells side by side with persistent PTYs, shared tooling, and recoverable session history.

* [agentjail v1.6.0](https://github.com/LuD1161/agentjail) – Policy guardrails for coding agents that locally check every tool call against OPA rules before execution.

* [sd0x-dev-flow v4.3.0](https://github.com/sd0xdev/sd0x-harness) – Harness layer for Claude Code that enforces hook-based review anchors, state-machine gates, and fail-closed safety for AI-assisted development.

* [Petdex desktop-v0.8.0](https://github.com/crafter-station/petdex) – Public gallery, CLI, and desktop app for browsing, installing, and running animated Codex companions.

* [PiDeck v0.7.0](https://github.com/ayuayue/PiDeck) – Electron-based desktop workbench for managing pi coding-agent sessions across project folders, with chat, skills, shell commands, files, and Git integration.

* [Token Monitor v0.44.0](https://github.com/Javis603/token-monitor) – Desktop widget that monitors live token usage and AI tool limits across multiple AI coding tools with real-time multi-device sync and usage history breakdowns.

* [brain.md v0.2.0](https://github.com/mindmuxai/brain.md) – A repo-native, agent-agnostic persistent memory layer that captures durable project decisions as Markdown via a zero-dependency CLI.

* [nodeterm v0.3.0](https://github.com/eneskirca/nodeterm) – Node-based terminal and AI session manager that maps persistent tmux sessions onto a draggable infinite canvas with optional Trello-style project boards.

* [HeiGe Codex Skin Studio v5.5.0](https://github.com/HeiGeAi/heige-codex-skin-studio) – One-click theme and skin switcher for Codex Desktop on macOS, using Chrome DevTools Protocol and image-based presets with customizable color kits.

* [BaoCut agent skill skill-v1.0.0](https://github.com/JimLiu/baocut) – Agent Skill that lets coding agents drive the BaoCut local bcut CLI and Subtitle Studio to transcribe, translate, edit, and export subtitles from natural language.

* [Code Kanban v0.44.0](https://github.com/fy0/CodeKanban) – Unified web interface to manage terminals, projects, AI coding agents, and task kanban.

* [sd0x-dev-flow v4.2.0](https://github.com/sd0xdev/sd0x-dev-flow) – Claude Code plugin enforcing hook-based dual review, auto-fix loops, and fail-closed quality gates.

* [Human Review v0.6.0](https://github.com/petergyang/human-review) – A visual editor for HTML and Markdown that lets users make direct changes and anchored comments, then sends all feedback to an AI agent in one batch.

* [yoloAI v0.11.0](https://github.com/kstenerud/yoloai) – Sandboxed runner for AI coding agents that keeps original project files untouched until you review diffs and apply chosen changes.

* [iLab CONJURE v0.8.0](https://github.com/kadevin/ilab-conjure) – iLab CONJURE is a FastAPI-based AI image generation WebUI and CLI with OpenAI-compatible and Codex Responses API support, featuring templates, chips, and local history queues.

* [Pagecast v0.7.0](https://github.com/Amal-David/pagecast) – Local-first publishing tool that previews and publishes HTML reports, Markdown docs, and static mini apps to shareable Cloudflare Pages URLs via a CLI or admin UI.

* [Claude Sidebar 1.9.0](https://github.com/derek-larson14/obsidian-claude-sidebar) – Embedded Obsidian sidebar terminal to run Claude Code with multiple tabs, folder-aware context, and YOLO mode.

* [Happy Coder cli-1.2.2](https://github.com/slopus/happy) – Mobile and web client providing end-to-end encrypted remote access and control for Claude Code.

* [Orca v1.4.190](https://github.com/stablyai/orca) – Cross-platform AI orchestrator for managing multiple worktrees, running concurrent coding agents, and tracking agent progress.

* [LiveAgent v1.2.7](https://github.com/Stack-Cairn/LiveAgent) – Local-first AI agent desktop client combining multi-model chat with local tool execution, MCP tool bridging, and a remote gateway for access and collaboration.

* [Codex Mate v0.1.14](https://github.com/SakuraByteCore/codexmate) – Local-first AI control plane for Codex, Claude Code, and OpenClaw with one-click provider/model/profile switching, safe config writes, unified session browser, and MCP stdio.

* [Sub2API v0.1.183](https://github.com/Wei-Shaw/sub2api) – AI API gateway that distributes subscription quotas, manages keys, billing, load balancing, and request forwarding.

* [Codex Security npm-v0.1.19](https://github.com/openai/codex-security) – A CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities in your code.

* [MemoraX Code v0.1.8](https://github.com/memorax-ai/memorax-code) – Memory plugin that adds cross-session repository knowledge, reusable lessons, and workflow preferences to multiple AI coding agents.

* [Metrik v0.18.0](https://github.com/keros68/metrik) – 桌面常驻工具用于统一查看本机各 AI 编程 Agent 的官方配额余量与 Token 消耗，支持 ChatGPT、Claude、GLM、Kimi 等。

* [WeSight v1.0.6](https://github.com/freestylefly/wesight) – Desktop AI agent workspace that installs and manages local coding agents with chat, tools, file and runtime monitoring, and model routing.

* [CodexHost v0.3.2](https://github.com/BytePioneer-AI/codex-host) – Codex Desktop integration that runs Pi, Claude Code, Grok Build, and DeepSeek Harness workloads with optional SSH agent hosting.

* [CLI WeChat Bridge 1.1.4](https://github.com/UNLINEARITY/CLI-WeChat-Bridge) – Bridges AI command-line tools into WeChat with bidirectional chat and thread/session sync between WeChat and the local terminal.

* [AgentReach v0.4.0](https://github.com/bojieli/agentreach) – AgentReach is a tool that proxies a coding agent’s shell and file operations over a single SSH connection so only the target is touched.

* [anywhere-agents v0.7.18](https://github.com/yzhao062/anywhere-agents) – Opinionated portable AI-agent configuration providing synced defaults, review workflows, and safety hooks across projects and sessions.

* [Claudexor v3.8.1](https://github.com/razzant/claudexor) – Local-first control plane that runs multiple AI coding agents via a typed interface, adding quota-aware routing, best-of-N races, and auditable execution evidence.

* [Daintree v0.33.0](https://github.com/daintreehq/daintree) – Daintree is a macro-orchestration app for running many AI coding agent terminals in parallel across git worktrees with context injection and workflow automation.

* [Agentfiles 0.8.1](https://github.com/Railly/agentfiles) – Obsidian plugin to browse, create, and manage agent skills across 13+ coding assistants.

* [Codex Command Center v0.1.0](https://github.com/sevensir888/codex-command-center) – Windows-first local-first desktop workspace that organizes Codex projects into tasks, session workflows, and Git change review with visible Codex Skills and MCP setup.

* [Claude Squad v1.0.20](https://github.com/smtg-ai/claude-squad) – Terminal app to manage multiple AI agents in separate git-backed tmux workspaces.

* [Wegent wework-v0.2.0](https://github.com/wecode-ai/Wegent) – Self-hostable platform for building and running AI agent teams across chat, coding, knowledge, and automation with shared capabilities and local execution via Wework.

* [LLMIO v0.8.13](https://github.com/atopos31/llmio) – Load-balancing gateway for multiple LLM provider APIs with REST compatibility.

* [UI Craft v1.0.19](https://github.com/educlopez/ui-craft) – Design engineering system for AI coding agents that produces scoreable, defensible UI critiques and guarded builds with craft-level polish.

* [agtop v0.5.1](https://github.com/ldegio/agtop) – Top-style terminal dashboard monitoring local AI coding agent sessions with live spend, token usage, context pressure, CPU, tool activity, and process details.

* [Codex App Manager v0.5.2](https://github.com/Wangnov/Codex-App-Manager) – Cross-platform desktop installer and updater that applies incremental updates, supports clean uninstalls, and performs China-reachable self-updates for the official Codex app.

* [tokless v0.3.2](https://github.com/HoangP8/tokless) – Unified pipeline that wires the best coding-agent tools with no config, enabling one-command setup and simple updates across macOS, Linux, and Windows.

* [Superset cli-latest](https://github.com/superset-sh/superset) – Terminal for running and managing 10+ parallel CLI coding agents locally.

* [Mimi Remote v0.3.0](https://github.com/gaixianggeng/mimi-remote) – Native local-first iPhone and iPad workbench for managing Codex sessions on your Mac, including reviewing diffs, approving actions, and handling Git work.

* [Scientific Illustrator v1.5.4](https://github.com/icebird1998/scientific-illustrator) – Tool that generates editable scientific figures for Microsoft PowerPoint, WPS, and draw.io using Codex-based quality gates.

* [Hevy MCP Server hevy-mcp@6.0.0](https://github.com/chrisdoc/hevy-mcp) – Hevy MCP server that lets AI clients securely read, analyze, and write workout data, including routines and templates, via authenticated Hevy API requests.

* [Honey (I Shrunk the AI) v1.3.1](https://github.com/Green-PT/honey-for-devs) – Cross-tool coding skill that reduces AI agent token usage by emitting less code and less prose while preserving correctness, with compact agent-to-agent handoffs and safety carve-outs.

* [reminal v3.1.8](https://github.com/harshalgajjar/Reminal) – Reminal streams and mirrors a machine’s real windows and full terminal into any browser with end-to-end encryption and no open ports.

* [VelaTerm v0.1.105](https://github.com/vlinx-io/VelaTerm) – A terminal manager that organizes AI coding sessions into a persistent project group session tree with agent-aware status and remote browser or SSH access.

* [CodeBurn desktop-v0.9.21](https://github.com/getagentseal/codeburn) – Interactive TUI dashboard that tracks token usage, cost, and performance across AI coding tools.

* [Maestro-Flow v0.5.82](https://github.com/catlog22/maestro-flow) – Workflow orchestration framework that routes intent to adaptive multi-agent command chains, runs parallel agents, and provides a real-time dashboard and evolving knowledge graph.

* [Clipal v0.23.4](https://github.com/PAIArtCom/Clipal) – Local LLM API gateway and manager that provides YAML-based routing, automatic failover, and a Web UI for multi-provider key and OAuth handling.

* [Joanium v2026.822.0](https://github.com/Joanium/Joanium) – Local-first AI desktop agent that runs scheduled background tasks, supports multi-model chat, and can use real integrations via MCP.

* [CLI-Manager V1.3.7](https://github.com/dark-hxx/CLI-Manager) – Centralized AI CLI workspace that manages multiple Claude/Codex sessions with hooks, token handling, and diff support to improve command workflow efficiency.

* [Tessera v0.2.3](https://github.com/horang-labs/tessera) – Web and desktop workspace that runs multiple AI coding agents side-by-side, tracking worktrees, diffs, and PRs.

* [Libretto v0.6.45](https://github.com/saffron-health/libretto) – Toolkit for building and maintaining web integrations, providing a live browser, network capture, action recording, and a token-efficient CLI for automation.

* [computer-use-linux v0.4.9](https://github.com/agent-sh/computer-use-linux) – Linux desktop control server and CLI for MCP hosts, offering AT-SPI accessibility, compositor-aware window targeting, screenshots, and input.

* [Lumen v0.0.42](https://github.com/ory/lumen) – Local semantic code search engine for AI coding agents using local embeddings and SQLite.

* [skillshare v0.20.25](https://github.com/runkids/skillshare) – Sync skills across multiple AI CLI tools including Claude, Codex, Cursor, Gemini, and Copilot with one command.

* [bb desktop-v0.35.1](https://github.com/get-bb/bb) – Agentic IDE that can orchestrate coding agents across desktop, web, CLI, and HTTP surfaces with controllable threaded work.

* [Mimi Remote v0.2.13](https://github.com/gaixianggeng/codex-ipad-agent) – A native local-first iPhone and iPad workbench for managing Codex sessions running on your Mac, with diff review, approvals, steering, and Git tasks.

* [Claude & Codex Usage Battery v2.6.3](https://github.com/dennykim123/claude-codex-battery) – macOS menu-bar and system-tray widget that displays Claude Code and Codex remaining usage limits as battery icons with reset-time details.

* [Shob v0.0.97](https://github.com/shobcoder/shob) – AI agent workspace for running parallel developer workflows with Git-aware operations, permissioned command approvals, and subagent delegation.

* [Better Agent v0.1.1](https://github.com/ofekron/better-agent) – Local workspace that runs multiple coding agents in one inspectable, persistent session history across trusted screens.

* [PR Cockpit nightly](https://github.com/taovc/pr-cockpit) – Local AI PR workbench that uses Claude or Codex to review PR queues in isolated worktrees, with human-gated GitHub inline comments.

* [CCG - Claude + Codex + Gemini Multi-Model Collaboration preset](https://github.com/fengshao1227/ccg-workflow) – Multi-model development system orchestrating Codex for backend and Gemini for frontend with Claude coordinating and reviewing patches.

* [Machinist factory-legacy-final](https://github.com/owainlewis/machinist) – Runtime and control plane that runs a supervised local team of coding agents to turn GitHub issues into reviewed pull requests.

* [Codex App Offline offline-v26.818.5229...](https://github.com/lusipad/unofficial-codex-app-offline) – Unofficial offline and portable repackaging for the OpenAI Codex Windows app with a local web gateway and Codex CLI.

* [DevWeek app-v0.1.5](https://github.com/JYYYYYT/dev-report-weekly) – Desktop app that uses AI to turn locally reviewed Git commits into editable weekly Markdown work reports, with commit filtering and checks.

* [AxonHub v1.0.0-beta7](https://github.com/looplj/axonhub) – Modern AI gateway providing unified OpenAI, Anthropic, and AI SDK-compatible APIs with tracing, project management, and developer tools.

* [OpenCove v0.2.0-nightly.20260...](https://github.com/DeadWaveWave/opencove) – Infinite 2D canvas workspace that organizes AI agents, terminals, tasks, and notes.

* [Atlas alpha-0.2.6](https://github.com/pacifio/atlas) – Atlas is a software factory that coordinates agent fleets across the full development lifecycle, sharing context and recording what agents change for searchable review.

* [Myrlin's Workbook v1.3.0-alpha.30](https://github.com/therealarthur/myrlin-workbook) – Workspace manager for Claude Code sessions with multi-pane embedded terminals, project discovery, kanban board, cost tracking, and session templates.

* [codex-app-linux v26.727.51351-launch...](https://github.com/better-slop/codex-app-linux) – Thin Linux launcher that bundles the Codex CLI runtime and downloads matching desktop binaries, then starts the app with CODEX\_CLI\_PATH; also ships npm, AUR, and a Nix flake.