{
  "markdown": "# AnyCap\n\n[![npm](https://img.shields.io/npm/v/@anycap/cli?color=cb3837&logo=npm)](https://www.npmjs.com/package/@anycap/cli)\n[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)\n[![GitHub stars](https://img.shields.io/github/stars/anycap-ai/anycap?style=social)](https://github.com/anycap-ai/anycap)\n[![Skills directory](https://img.shields.io/badge/skills.sh-anycap-6f42c1)](https://skills.sh/anycap-ai/anycap)\n\n> **The capability runtime for AI agents.**\n>\n> Give coding agents a single CLI, Agent Skill, and local MCP server for creating media,\n> understanding files, researching the live web, and delivering results people can use.\n\n![AnyCap — the capability runtime for AI agents](assets/hero.png)\n\n## Start here\n\nGive this to Claude Code, Codex, Cursor, or another agent that can run shell commands:\n\n```text\nRead https://raw.githubusercontent.com/anycap-ai/anycap/main/llms.txt and follow its\ninstructions to install and configure AnyCap.\n```\n\nIf your agent cannot reach that URL, use the manual setup below.\n\n```bash\n# Install the CLI (macOS, Linux, or Windows through Git Bash)\ncurl -fsSL https://anycap.ai/install.sh | sh\n\n# Install the AnyCap Agent Skill\nnpx -y skills add anycap-ai/anycap -s '*' -g -y\n\n# Authenticate once, then confirm the runtime is ready\nanycap login\nanycap status\n```\n\nThe binary installer is the recommended path. If your environment already uses Node.js,\nyou can instead run `npm install -g @anycap/cli`. Platform binaries are also available\nfrom [GitHub Releases](https://github.com/anycap-ai/anycap/releases).\n\n## Choose an integration\n\n| Integration | Use it when | Entry point |\n| --- | --- | --- |\n| **Agent Skill** | You want an agent to choose the right workflow from a natural-language request. | [`skills/anycap-cli/SKILL.md`](skills/anycap-cli/SKILL.md) |\n| **Agent plugin** | You want to install the complete Skills collection through Claude Code or Codex. | [`.claude-plugin/plugin.json`](.claude-plugin/plugin.json) / [`.codex-plugin/plugin.json`](.codex-plugin/plugin.json) |\n| **Local stdio MCP** | Your agent host needs typed tool discovery. | `anycap mcp` |\n| **CLI** | You want shell automation or direct control. | `anycap <command>` |\n\nAll integrations use the same installed runtime and authentication state. The Skills and\nMCP server can be used together.\n\n### Install as an agent plugin\n\nThe repository declares the complete `skills/` tree as both a Claude Code plugin and a\nCodex plugin. Both hosts use the marketplace in `.claude-plugin/marketplace.json`; the\nCodex metadata in `.codex-plugin/plugin.json` points at the same shared Skills collection.\n\nIn Claude Code, add the marketplace and install the plugin:\n\n```text\n/plugin marketplace add anycap-ai/anycap\n/plugin install anycap@anycap\n```\n\nFrom a shell with Codex installed, run:\n\n```bash\ncodex plugin marketplace add anycap-ai/anycap\ncodex plugin add anycap@anycap\n```\n\nThe plugin installs the Skills collection only. Install the AnyCap CLI, run `anycap login`,\nand verify `anycap status` before using those Skills.\n\n### Connect through MCP\n\nFirst confirm that the installed CLI exposes the server:\n\n```bash\nanycap mcp --help\n```\n\nFor Codex, add the local server definition:\n\n```bash\ncodex mcp add anycap -- anycap mcp\n```\n\nFor a generic stdio MCP client, configure `anycap mcp`. Add a narrowly scoped\n`--allow-root` only when the server needs to access local media:\n\n```json\n{\n  \"mcpServers\": {\n    \"anycap\": {\n      \"type\": \"stdio\",\n      \"command\": \"anycap\",\n      \"args\": [\"mcp\", \"--allow-root\", \"/absolute/path/to/media\"]\n    }\n  }\n}\n```\n\nDo not commit personal absolute paths into shared project configuration. Read the\n[MCP setup guide](https://docs.anycap.ai/getting-started/mcp/) and\n[security guide](https://docs.anycap.ai/reference/security/) before granting local\nfile access.\n\n## What agents can do\n\n| Area | Examples |\n| --- | --- |\n| **Create** | Generate and edit images, generate video, compose music, and create audio scenes. |\n| **Understand** | Read screenshots, compare images, summarize video, and transcribe or analyze audio. |\n| **Research** | Search the live web and crawl pages into Markdown. |\n| **Collaborate** | Gather visual annotations and work with shared drawing surfaces. |\n| **Deliver** | Upload and share files, publish static sites, and create project snapshots. |\n\nFor a first end-to-end workflow, see [generate and share an image](https://docs.anycap.ai/guides/generate-and-share-image/).\nOther task-oriented guides cover [image-to-video](https://docs.anycap.ai/guides/image-to-video/),\n[human feedback](https://docs.anycap.ai/guides/human-feedback/),\n[web research](https://docs.anycap.ai/guides/web-research/), and\n[static-site publishing](https://docs.anycap.ai/guides/publish-site/).\n\n## Discover live capabilities\n\nModel availability and input schemas change. Query the installed CLI instead of copying\nmodel IDs or parameters from an old example:\n\n```bash\n# List models available to your account\nanycap image models\nanycap video models\nanycap music models\n\n# Inspect the current modes and schema for a selected model\nanycap image models <model-id>\nanycap image models <model-id> schema --mode <mode>\n```\n\nRun `anycap --help` at any level to inspect commands and options:\n\n```bash\nanycap --help\nanycap image --help\nanycap image generate --help\n```\n\n## Documentation and support\n\n- [Documentation](https://docs.anycap.ai/) — quickstart, capability guides, and reference material.\n- [CLI reference](https://docs.anycap.ai/reference/cli/) — command groups, output conventions, and discovery.\n- [MCP tool reference](https://docs.anycap.ai/reference/mcp-tools/) — current tools and read/write boundaries.\n- [Authentication and configuration](https://docs.anycap.ai/getting-started/authentication/) — interactive, headless, and API-key workflows.\n- [Troubleshooting](https://docs.anycap.ai/getting-started/troubleshooting/) — installation and runtime diagnostics.\n- [`llms.txt`](llms.txt) — concise installation and usage instructions for agents.\n- [Skills directory](https://skills.sh/anycap-ai/anycap) — install the Agent Skills collection.\n\n## Updating\n\nThe CLI checks for updates during normal use. Update it explicitly when needed:\n\n```bash\nanycap update\nnpx -y skills update\nanycap status\n```\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 6309,
  "sha": "bd7afced35645d0b617b5e923d5ddbeea6a79a5855b0ab59c85bdf1f1b912c51",
  "repo_slug": "anycap-ai/anycap",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_anycap_ai_anycap_c052745a/readme"
}