Codex 17

Skilloop is an Agent Skills directory for Claude Code, Codex & Cursor. Preview skill outputs before install. Chinese: https://skilloop.dev/zh | Skills: https://skilloop.dev/skills | Examples: /zh/ai-video/fable-5-5, /zh/ai-video/opus-5-5 | GitHub: https://github.com/xianyu110/skillhub

Modelflare is a stable, lower-cost API gateway for GPT, Claude, Grok, GLM, Seedance, MiniMax, and other models, with routes as low as 1.5% of the official price. The same account opens Castaly, a studio for generating images and video, comparing models and prices, and remixing community work. Modelflare is one API gateway for apps, agents, and coding tools. Keep the client you already use, point it at https://modelflare.dev/v1, and call many model families with the same key. Lower price. Selected routes bill down to 1.5% of the official list price. A single top-up of US$20 unlocks GPT at that 0.015x rate. Everyday traffic can stay on a lower-cost group; more sensitive jobs can use a balanced or higher-stability group. The pricing page shows what you pay against the official list price. Balance is in US dollars: one dollar of top-up is one dollar of credit. Castaly uses that same balance. A key can list fallback groups in order. If the primary group is unavailable, the request moves to the next group. Each request records status, latency, token usage, and cost, whether it came from your own code or from Castaly. Many models, one account. GPT uses OpenAI Chat Completions and the Responses API, including Codex-style clients. Claude uses Anthropic Messages, including Claude Code. Grok, GLM, Seedance, and MiniMax are on the same key, along with DeepSeek, Kimi, Owen, Gemini, and image and video models. Castaly (https://castaly.modelflare.dev) is the studio on that account. In the browser you generate images and video with Seedance, Kling, Wan, MiniMax, Seedream, and other models from the same catalog. You compare specifications and price, set the shot parameters, and remix a community work from its prompt and settings. Account, balance, API keys, and usage history are shared with Modelflare, so a result made in Castaly can also be requested through the API. Create a key at https://modelflare.dev, set the base URL to https://modelflare.dev/v1, or start a shot in Castaly.

Skillry is a growing library of Agent Skills for AI coding agents. Every Skill carries a specific visual point of view, and you can see exactly what it makes before you install it — so what your agent ships is something you'd actually show. Web pages, slide decks, images and video. Install from the web or your CLI and use it inside Claude Code, Codex, Cursor and more. The taste is ours. The work is your agent's. Your agent can build a site, a deck, a video, an image. It just has no taste. Skillry is a growing library of Agent Skills that do. Each Skill carries a specific visual point of view, and you can see exactly what it makes before you install it — you are not buying a description. Install from the web, or authorize your browser once and run a single command in your CLI. Then invoke a Skill by name inside your agent and get a finished piece of work: a landing page that looks art-directed, a deck you would actually present, an image that stops the scroll, a short film that moves. Four kinds of work today — web pages, slide decks, images and video — with new Skills added every week. No API key required. It is not a marketplace. There is no community upload and no race to ten thousand listings. The library is deliberately small and grows one Skill at a time, which is the whole point: everything in it has a look worth keeping. Works with Claude Code, Codex, Cursor and more. The taste is ours. The work is your agent's.

AI-driven video editor for humans, developers, and coding agents Diffusion Studio is an open-source, AI-driven professional video editor for humans and coding agents. It combines an infinite canvas, timeline sequencing, media import, video editing, effects, audio tools, transcription, AI generation, and export in one workspace. Users can work in a browser, on macOS, or through the terminal, while agents such as Claude Code, Codex, and Cursor can analyze, edit, generate, and transcribe footage. The editor supports 4K playback and export, no-watermark exports, commercial use, and responsive canvas performance.

AI subscription payment service — activate ChatGPT Plus, Claude Pro, Codex and more with Alipay or WeChat Pay in minutes. CZGPT is a self-service subscription payment platform for activating premium AI subscriptions — including ChatGPT Plus, ChatGPT Pro, Codex, Claude Pro, Gemini, Grok, and Suno — using Alipay or WeChat Pay, with no international credit card required. Many users cannot complete AI subscription payments because their cards are declined by international payment systems. CZGPT solves this: pay in RMB via Alipay or WeChat Pay, receive an activation key automatically within 1–2 minutes, and complete the upgrade yourself through a guided redemption flow. No account password is ever required, and each order activates an independent subscription on your own account. Key capabilities: - One platform covering all major AI subscriptions (OpenAI, Anthropic, Google, xAI, Suno) - Alipay and WeChat Pay support with instant automated key delivery - Self-service redemption — you keep full control of your account credentials - Typical activation completed within 2–5 minutes - Full refund if an activation cannot be completed - Order lookup and human customer support Use cases: - Subscribing to ChatGPT Plus/Pro with Alipay or WeChat Pay instead of a foreign credit card - Developers activating Codex or Claude Pro subscriptions for AI coding tools - Teams activating multiple independent AI subscriptions, one per account - Renewing AI subscriptions monthly with full spending control (no auto-charge) CZGPT also maintains a free, continuously updated guide covering AI subscription methods, common payment errors, and troubleshooting.

Cloud development environments designed for running parallel AI coding agents. Boxes.dev is a cloud development environment platform specifically built for agentic coding. It provides full, isolated Linux virtual machines (VMs) for each individual Claude Code or Codex chat thread. This allows developers to run coding agents in parallel, let them work overnight while the laptop is closed, and monitor or steer them seamlessly from mobile, desktop, or CLI interfaces without resource constraints or complicated dev setup scripts.

ChatGPT Plus、Pro代充值，正规渠道充值到本人账号，并提供30天质保，支持企业采购服务。充值不成功5分钟内退款。 GetPlus 提供 ChatGPT Plus、ChatGPT Pro正规渠道代充值服务。会员直接充值到用户本人账号，全程无需提供账号密码，大多数订单通常在1–2分钟内到账。 符合质保规则的订单提供30天质保。个人用户可以通过 GetPlus 网站、淘宝或闲鱼下单。 企业客户支持开具发票、签订对公采购合同、对公转账以及团队批量采购。

Open-source workspace for running and managing AI coding agents ADE is a local-first, open-source Agentic Development Environment that brings AI coding agents such as Claude Code, Codex, Cursor, Factory Droid, and OpenCode into one synchronized workspace. It runs across macOS, Windows, Linux, the web, terminal, and iOS, allowing developers to manage parallel coding tasks using isolated Git worktrees, agent chats, terminals, pull requests, built-in tools, and remote machines.

Open-source SDK to run coding agents in secure sandboxes. VibeKit is an open-source SDK designed to run coding agents like OpenAI Codex and Claude in secure sandboxes. It enables agents to write code, install packages, or open PRs safely, with built-in streaming, async tasks, and telemetry. MIT licensed and built with TypeScript, it offers zero lock-in. VibeKit allows developers to embed coding agents into their applications or workflows, supporting various sandbox providers such as E2B, Daytona, Modal, and Fly.io. It is ideal for creating internal tools, adding AI-powered features to apps, and streamlining prototyping workflows.

Background coding agents running in sandboxed dev environments Replicas is a platform that allows engineering teams to run background coding agents like Claude Code or Codex from anywhere. It spawns these agents inside isolated, sandboxed development environments (virtual machines) equipped with the necessary code and tooling. Teams can hand off coding tasks directly through integrations with Slack, Linear, or GitHub, allowing agents to automate code changes, install dependencies, run databases, and verify changes locally, ultimately returning a pull request ready for human review.

Open-source workspace for managing multiple coding agents T3 Code is an open-source control plane for coding agents. It provides one interface for orchestrating Claude Code, Codex, OpenCode, Cursor, Grok, and other coding harnesses using subscriptions and credentials that users already own. The application supports agent workflows, model switching, GitHub branch and pull request management, inline diff review, self-hosting, forking, and custom tooling. It is available for Windows, Linux, iOS, and Android, and is MIT licensed.

AI platform for building and shipping native Swift apps Bitrig is an AI-powered development environment for building and shipping native Swift apps across Apple platforms. Users describe an app idea in natural language, and Bitrig generates real Swift code and full Xcode projects using AI agents powered by Claude Code and Codex. It includes built-in simulators, automated testing, code editing, GitHub integration, backend support through CloudKit or Supabase, App Store and TestFlight publishing, in-app purchase configuration, and remote development through iPhone or iPad. Bitrig supports platforms and technologies including iOS, iPadOS, macOS, watchOS, tvOS, visionOS, Widgets, Live Activities, App Intents, Siri, Shortcuts, Spotlight, Push Notifications, StoreKit, and RevenueCat.

AI token optimization stack for reducing agent costs and context Caveman is an AI efficiency operating stack that reduces the cost and context size of agent-native development. It provides an MIT-licensed skill, a free local proxy, an Agent SDK, and planned cloud and enterprise services. Caveman compresses logs, JSON, code, diffs, tables, tool outputs, and files before provider calls while preserving recoverable original bytes. It also supports caching, eval-gated model routing, token usage visibility, savings estimates, and verification workflows. The local wrap works with users' own provider keys and does not require a Caveman account.

Local CLI that reduces coding-agent token waste JFrog Boost is a free, local-first command-line tool that compresses noisy terminal output, MCP responses, file contents, and other tool data before it reaches coding agents such as Cursor, Claude Code, Codex, GitHub Copilot, and OpenCode. It reduces token usage while preserving important information such as errors, failures, summaries, and relevant context. Boost uses reversible compression and retrieval, allowing agents or developers to restore the original output when needed. It also provides graph-based code retrieval, file optimization, observability, telemetry, and enterprise-focused privacy.

A shared company brain for AI knowledge, skills, and workflows HQ is a shared company knowledge and workflow platform that provides the context layer for AI tools. It brings team knowledge, projects, reusable skills, workflows, secrets, and connected systems together in a workspace the company owns. HQ works across tools including Claude Code, Codex, Cursor, ChatGPT, and Claude, helping teammates and AI bots reuse shared context instead of starting from scratch.