Claude Code 45

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

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.

Largest library of 90,000+ Agent Skills with real-world Use Cases & Community Reviews. Access 90,000+ verified Claude Agent Skills designed for high-performance automation. Every skill includes detailed use cases and peer reviews to ensure reliability. Stop prompting from scratch and deploy expert-level AI modules in seconds.

Shared project workspace for teams using AI coding agents Joxo is a shared collaboration project for teams using AI coding agents such as Claude Code, Codex, Cursor, Gemini CLI, and OpenCode. It connects each teammate’s existing coding-agent sessions through shared project memory, tasks, decisions, blockers, and handoffs. Joxo does not provide or resell AI models, subscriptions, or API access; each person uses their own AI provider account and computer. The service relays intentionally published project information between agents, helping teammates continue work without repeating context or sharing screenshots.

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.

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 Agent Development Environment for parallel AI coding agents. Orca is an open-source, cross-platform Agent Development Environment (ADE) specifically designed for running and orchestrating AI coding agents. Unlike traditional IDEs, Orca allows developers to run multiple AI command-line interface (CLI) agents—such as Claude Code, Codex, Gemini, and OpenCode—simultaneously in isolated git worktrees. This parallel setup enables users to multi-task across branches, test solutions, and review AI outputs efficiently within an environment featuring Ghostty-inspired WebGL terminals, an embedded Chromium browser for Design Mode feedback, native GitHub/Linear integration, and an editor.

OpenAI-compatible AI gateway for Claude, GPT & more — swap one base_url. CodeGateway is an OpenAI-compatible AI gateway that gives developers unified access to Anthropic's Claude, OpenAI's models, and more through a single endpoint. Because it speaks the standard OpenAI API format, any tool you already use — Claude Code, Cursor, Codex CLI, Cline, Continue — works after a one-line change to the base_url. No SDK swap, no code rewrite. Smart routing picks a backend by latency and cost and fails over automatically during peak load, so requests stay reliable. Responses stream in real time over SSE, and Anthropic-compatible and Codex Responses endpoints are supported too. Built-in usage analytics give you real-time token usage, model distribution, and cost breakdowns you can export for audit anytime. Billing is pay-as-you-go with no subscription and no monthly minimum: top up from $5, every new account gets $2 of free trial credit, and payments accept cards as well as Alipay and WeChat Pay. Integrate in about five minutes and switch models without rewriting your code.

AgentGit makes every agent session easy to save, share, and continue. Every AI agent session contains more than a final result. It records the instructions, attempts, tool calls, discoveries, and decisions that shaped the work. AgentGit is version control and a collaboration hub for these sessions. It lets users save an agent conversation, return to it later, continue it from another device, hand it off to a teammate or another agent, or share it through a secure read-only link. Users can also return to an earlier turn and explore a different direction without losing the original work. With Remote Control, users can access an agent running on their own computer from a phone or browser. Teammates can be invited to follow progress, send prompts, and handle delegated approvals. The Agent Session Hub also makes it possible to explore how other people solve problems and share successful agent workflows with the community. AgentGit works with popular AI agent environments, including Claude Code, Codex, OpenCode, Cursor, and more. Available import, resume, and remote-control capabilities may vary by runtime. AgentGit is designed for vibe coders, independent makers, developers, product teams, and anyone using AI agents to complete real projects. It works alongside the project’s existing code repository, keeping conversation history separate from source-code version control.

Prompt-first IDE for AI power users with parallel sessions and atomic branching. Dereference AI Codetabs is a prompt-first IDE built for Claude Code power users and other CLI AI tools like Gemini CLI. It offers features such as running parallel AI sessions, setting checkpoints for instant branching or resuming, and working like tmux but smarter. The IDE is designed to supercharge developer workflows and unlock true 100x developer velocity by providing multi-session orchestration, atomic branching, lightning-fast native performance, privacy-first design, seamless AI tool integration, and intelligent context management.

Open-source skills system providing product methodology and business context to AI agents. Baseline Studio offers Baseline Core, an open-source skills system designed to give AI agents professional product methodology. By running a simple CLI command, it installs a suite of 12 skills, 14 frameworks, and 34 reference files into a project. This system grounds AI tools like Claude Code, Cursor, and ChatGPT in a company's specific business context, enabling them to perform high-level tasks such as market research, PRD writing, sprint planning, and UX design with the consistency and quality of a senior product manager.

Codebase intelligence for documentation, AI context, health analysis, and safer software changes Repowise is codebase intelligence software that analyzes source code, dependencies, call relationships, Git history, ownership, tests, security signals, and architectural decisions. It converts this evidence into a reusable codebase model, source-linked documentation, dependency graphs, health scores, change-risk analysis, and grounded answers for developers and AI coding agents. Repowise supports MCP tools for Claude Code, Cursor, and other compatible clients, as well as hosted repositories, GitHub pull request reviews, team workspaces, and self-hosting through its AGPL-3.0 open-source core.

Collaborate with local AI agents in shared team rooms Alook is an AI agent collaboration platform that lets people and locally running AI coding agents share the same servers, channels, and direct messages. It gives agents persistent identities, handles, inboxes, memberships, and memory while keeping their runtime, tools, credentials, and codebase access on the user's own machine. Alook connects existing agents such as Claude Code, Codex, Cursor, OpenCode, and Pi to shared rooms so teams can communicate with and delegate work to them directly. The room layer is hosted by default but can also be self-hosted, and the project is open source under the Apache-2.0 license.

Export and share Claude Code terminal sessions as navigable, embeddable web URLs. Claudebin is an open-source tool designed for users of Claude Code (Anthropic's terminal-based AI). Since Claude Code stores session data locally in a non-human-readable format, Claudebin allows users to export these sessions into shareable, navigable, and embeddable web artifacts. It captures the complete context of a session, including message threads, file reads and writes, bash commands, and MCP calls, providing a structured viewer via a unique URL. This makes it possible to share terminal interactions in pull requests, documentation, or to resume them on different local machines.

A browser-based agent-native computer for running autonomous AI agents in secure sandboxes. happycapy is an agent-native computer designed for developers and creators that runs directly in the browser. it provides a secure, isolated sandbox environment where AI agents, including Claude Code, can work 24/7. The platform transforms traditional command-line interfaces into a visual desktop GUI, allowing users to watch agents work, delegate complex tasks through built-in 'skills,' and receive completed work via email. It supports over 150 AI models and offers features like task automation and a skill store, effectively turning the browser into a powerful, autonomous workstation.

Curated community registry for Claude Code and OpenAI Codex plugins and agentic skills. Claude & Codex Plugins is a curated community registry and discovery platform for developers using AI coding agents like Claude Code and OpenAI Codex. It provides a ranked list of the most useful plugins, tools, and agentic skills based on actual installation data rather than marketing hype. The site covers a wide range of categories, including codebase intelligence, memory upgrades, SEO analysis, cybersecurity, and specialized development workflows. It simplifies the process of finding and installing community-contributed enhancements for terminal-based AI tools, offering direct installation commands for various tools including Cursor, Gemini CLI, and Antigravity.

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.

Centralized rule management and plan validation for AI coding agents like Cursor and Claude. Straion is a centralized rule management platform designed for AI coding agents such as Claude Code, GitHub Copilot, and Cursor. It allows engineering teams to define architecture standards, security policies, and coding guidelines in one central hub rather than scattered markdown files. The platform automatically injects the relevant context into AI prompts based on the specific task and validates AI-generated plans before the coding starts. This ensures that AI agents remain aligned with organizational standards, reducing the need for manual code review and preventing 'AI drift' while maintaining high development velocity.

A marketplace for finding and exploring open-source AI agent skills. The Agent Skills Marketplace is an independent community project that aggregates and showcases over 61,000 open-source agent skills sourced from GitHub repositories. It is designed to help users quickly find skills compatible with AI coding assistants like Claude Code, OpenAI Codex, and ChatGPT. The platform offers smart search (AI semantics or keywords), category filtering, and quality indicators. All listed skills adhere to the open SKILL.md standard, making them ready to install and use to extend the capabilities of AI coding assistants.

Monitor and control AI coding agents from your Mac notch Crew Tower is a native macOS control center for monitoring and managing AI coding agents from the MacBook notch or a floating pill on external displays. It supports agents such as Claude Code, Codex, Cursor, Gemini CLI, Qwen Code, and OpenCode. Users can review permission requests, approve or deny commands, answer agent questions, review plans, monitor progress and context usage, receive completion notifications, and jump directly to the correct terminal tab without leaving their current work. Crew Tower communicates locally through agent hooks and Unix sockets, keeping code, prompts, and transcripts on the Mac.

A macOS workspace for orchestrating parallel AI coding agents and automating development workflows. Scape is a macOS application for running and managing unlimited Claude Code, Codex, and OpenCode agents across isolated Git worktrees. It provides a visual workspace for parallel agent sessions, watchdogs, automation playbooks, tables, orchestration through Argus, agent collaboration, encrypted chat rooms, voice transcription, and development tools. Scape is local-first, so projects and workflows remain on the user's machine, while users continue using their existing AI agent subscriptions.

macOS app factory for creating sandboxed, native terminal apps for TUI programs. Multitui is a macOS app factory designed to convert Terminal User Interface (TUI) programs into dedicated, native macOS applications. It allows users to wrap command-line tools like Claude Code, lazygit, htop, and vim into individual .app bundles with their own dock icons and window management. A standout feature is its integrated sandboxing, which leverages macOS's built-in sandbox-exec to provide fine-grained filesystem protection. This ensures that CLI tools or AI agents can run with restricted permissions, preventing them from deleting or modifying sensitive data unless explicitly allowed. Each app maintains its own shell history, snippets, and visual themes, providing a first-class macOS experience for power users.

Remote terminal streaming for monitoring AI CLI tools from mobile devices. SessionCast is a remote terminal streaming platform designed for developers to access and monitor their local terminal sessions from any device, including smartphones and tablets. It is specifically built to support the 'AI coding era,' allowing users to keep track of long-running tasks from tools like Claude Code, Cursor, and GitHub Copilot CLI without being tethered to a desk. By using a lightweight local agent and a secure relay server, it eliminates the need for complex VPN setups, SSH configurations, or port forwarding. It features low-latency bidirectional communication, allowing users to not only monitor progress but also enter commands remotely through a mobile-optimized interface.