One playbook. Every agent.

Skills, MCP servers, project instructions, and memory in one portable source of truth — deployed to Claude Code, Cursor, Codex, Antigravity, and Hermes from a single command.

Claude CodeCursorCodexAntigravityHermesCustom GPTsGemini GemsLocal LLMsAgent SkillsSKILL.mdAGENTS.mdMCP ServersCursor RulesAgent Memory

Open source and self-hostable. For software agents today, physical robots tomorrow. 🦉

Core Concept

What is a Playbook?

A Playbook is the complete operating environment for an AI agent - everything it needs to work effectively, all in one place.

Think of it as your agent's portable work profile: a source of truth that travels with you across platforms and vendors.

Persona

Personality & Style

The agent's base personality, communication style, and system prompt. This defines HOW the agent behaves and responds.

Skills

Knowledge & Capabilities

Structured task definitions and knowledge the agent can use. Skills define WHAT the agent knows and can do. Later: attach documents for deeper knowledge.

MCP Servers

Tools & Integrations

External tools and APIs the agent can access via Model Context Protocol. Code execution happens at the agent itself - these are the connections.

Coming Soon

Canvas

Working Documents

Structured markdown documents that serve as the agent's workspace. Notes, drafts, project files - persistent documents the agent can read and write.

Memory

Persistent Context

Key-value storage for remembering facts, preferences, and state across sessions. The agent's long-term memory.

Everything Your AI Needs

Personas
Define system prompts and AI personalities that work across any platform
Skills
Create reusable capabilities and task definitions in Anthropic skill format
MCP Servers
Configure Model Context Protocol servers for tools and resources
Coming Soon
Canvas
Structured markdown documents as the agent's persistent workspace
Memory
Persistent key-value storage your AI can read and write to
AI Platform Compatible
Use standard formats across Claude, ChatGPT, Gemini, Cursor, Codex, local models, and more - without vendor lock-in
API Key Access
Let your AI write back - update memory, skills, and personas programmatically

How It Works

01

Create a Playbook

Define your personas, skills, and MCP configurations in one place

02

Publish & Share

Get a unique URL that serves your playbook in any format

03

Connect Your AI

Give the URL to your GPT, Claude, or any AI agent

Real Problems, Real Solutions

Sound Familiar?

Real problems that AgentPlaybooks solves

Want to switch from ChatGPT to Gemini, but can't take your memory and conversations with you?

Your playbook travels with you. All personas, skills, and memories are stored platform-independently - just point your new AI to your playbook URL.

Built amazing skills in Claude, but want to use them in other platforms too?

Skills in your playbook work everywhere. Export in Anthropic format, OpenAPI for GPTs, or any other format - your investment isn't locked to one vendor.

Love Grok but miss ChatGPT's custom actions and integrations?

Define your MCP servers and tools in your playbook - any AI that supports tool use can access them, regardless of platform.

Your team uses different AI platforms, but needs consistent behavior?

Share a playbook URL. Everyone's AI - whether Claude, GPT, or local LLM - follows the same guidelines and has access to the same skills.

Worried about being locked into today's AI platform?

AgentPlaybooks is open source with standard formats. Your playbooks will work with tomorrow's AIs and robots - we're building for the future.

Running local LLMs but want the same capabilities as cloud services?

Point your local model to your playbook. Same skills, same persona, same memory - just running on your hardware.

100% Open Source

Your Agent Knowledge, Your Control

Zero vendor lock-in. Portable skills. Self-hostable. The knowledge your agents accumulate is valuable - keep it yours.

Skills Marketplace

Browse, share, and discover community-created skills. Like an app store, but for AI capabilities.

Self-Host Anywhere

Run on your infrastructure - on-premise, private cloud, or air-gapped. Full control, full privacy.

Platform Independent

Works with Claude, ChatGPT, local LLMs, and future robots. Switch platforms without losing knowledge.

Community Library

Community Repository

Browse public skills, personas, and MCP servers built by the community, and install any of them into your own playbook. For software agents today, physical robots tomorrow.

What is AgentPlaybooks?

AgentPlaybooks is a portable operating environment for AI agents. A playbook holds everything an agent needs to work — its persona, its skills, its MCP servers, its project instructions, and its memory — as one source of truth that belongs to you rather than to any single vendor.

One playbook, every agent: the same configuration deploys to Claude Code, Cursor, ChatGPT and Codex, Google Antigravity, Hermes Agent, and local models — each in the file layout that tool expects, with drift between copies detected rather than discovered later. Credentials stay out of it: a playbook declares which secrets it needs, and the values are injected server-side so they never reach an agent's context or your disk.

🤖 For AI Agents

  • • One set of instructions, every tool
  • • Agent Skills in SKILL.md format
  • • MCP servers, federated and proxied
  • • Memory and canvas that survive a session

🔧 For Developers

  • • Export to OpenAPI for GPT Actions
  • • Anthropic Skills format support
  • • JSON Schema definitions
  • • Self-host on your infrastructure

Open source and self-hostable, so the playbook is the portable source of truth — not any single vendor or editor. Switch platforms, run several at once, or host the whole thing yourself. Built for coding agents and AI assistants today, and for the physical robots that will need the same portable skills tomorrow.