
AgentPlaybooks
Actively maintained
- Is it safe? Its policy says it does not train on your data.See ↓
- Is it free? We have not read the prices of AgentPlaybooks yet; they are next in our queue. Until then, the official site has them.agentplaybooks.ai ↗
- What else does this?
OpenCodefree
Pi Coding Agent
CosmicfreeSee ↓
not read yet
Use
- For
- people running AI agents across Claude, ChatGPT, Cursor or local models who want portable instructions and memory
- Activity
- Actively maintainedsite updated 5 days ago
- How it runs
- Self-hosted
- Used for
- move chatbot memory and conversations between AI platforms
- share one agent setup across a team's AI tools
- reuse skills in Claude, custom GPTs and local models
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsagentplaybooks.ai ↗
- Trains on your dataNoprivacy policy ↗
- Certifications they stateGDPRprivacy policy ↗
- Privacy policy updated2026-10-10privacy policy ↗
“AgentPlaybooks does not run AI models, and your content is not used to train any.”
privacy policy ↗
These are AgentPlaybooks's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.
- MCP serverai.agentplaybooks/agentplaybooksverified in the MCP registry
- Stateanswers, requires sign-inchecked 2026-10-29
- Address to connectagentplaybooks.ai/api/mcp/manage
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1

OpenCode
Open source coding agent that generates code in terminal, IDE, or desktop app with support for multiple LLM providers.
108kActiveOpen source2025 - #2

Pi Coding Agent
Minimal agent harness for building custom coding workflows with extensible skills and multi-model support.
208kActive - #3

Cosmic
Headless CMS that stores structured content in custom models and serves it over REST and GraphQL APIs to websites and apps.
11kActiveFrom $99/mo2016 - #4

Agent37
Hosts and deploys AI agents with one-click setup or API integration, supporting multiple models and 1000+ tool integrations.
2.2kActiveFrom $0.80 per use - #5

OhmyposhMCP · open
Renders customizable shell prompts from a single config, running segments like git status and language versions concurrently.
6.9kActive
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use AgentPlaybooks for?
Sign in to leave a noteWhat is AgentPlaybooks?
Stores an agent's personas, skills, MCP configs and memory as one portable playbook rendered for Claude, Cursor, Codex and other platforms. It is listed in the Atlas under Developer tools.
Who is AgentPlaybooks for?
people running AI agents across Claude, ChatGPT, Cursor or local models who want portable instructions and memory
Is AgentPlaybooks still maintained?
Actively maintained: site updated 5 days ago.
Does AgentPlaybooks train AI on your data?
No, per its privacy policy (2026-10-29): “AgentPlaybooks does not run AI models, and your content is not used to train any.”
Is AgentPlaybooks safe?
We do not audit vendors. What AgentPlaybooks publishes, read 2026-10-29: GDPR stated on its privacy policy; on training with your data, “AgentPlaybooks does not run AI models, and your content is not used to train any.”.
What are alternatives to AgentPlaybooks?
In Developer tools, by use: OpenCode, Pi Coding Agent, Cosmic, Agent37, Ohmyposh.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.