Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.charmos.io/llms.txt

Use this file to discover all available pages before exploring further.

Charm Banner
Bring your AI agents to everyday users

Get Started

Install the Charm CLI with pip or uv and publish your first agent in minutes.

Onboarding

Walk through the full CLI workflow — from init to push — with guided examples.

Templates

Start from a prebuilt template: research agents, code reviewers, Slack bots, data pipelines, and more.

​
What is Charm?

Charm is a unified application layer that provides a standardized architecture for distributing, running, and scaling AI agents across heterogeneous ecosystems — turning them into real, commercial-ready applications with a single manifest file and a few CLI commands.

​
Why Charm?

  • Ecosystem Agnostic: Bring your own framework — CrewAI, LangChain, LangGraph, OpenClaw, or plain Python functions — Charm wraps them all with the same runtime contract.
  • No Infrastructure: The Cloud Runner handles isolated container execution, secrets injection, and scaling. You write agent logic, not deployment pipelines.
  • Server-Driven UI: Return Markdown or structured JSON from your agent and the Store renders timelines, comparison tables, viral cards, and article layouts automatically — no frontend code needed.
  • Built-In Monetization: Set pricing in charm.yaml and Charm handles checkout, subscriptions, wallet balance checks, and creator payouts through Stripe.
  • Open Source: Charm SDK, CLI, and runtime adapters are open source under AGPLv3. Community contributions drive new adapters, base images, and skills.

​
Who needs Charm?

  • AI engineers who have a working agent in CrewAI, LangChain, or custom Python and want to ship it as a product without building infrastructure.
  • Indie builders who want to monetize agents through the Charm Store with built-in billing, OAuth, and a hosted runtime.
  • Teams that need to standardize how agents are packaged, versioned, deployed, and observed across projects.

​
What do you need?

  • Python 3.10+ and pip or uv for package management.
  • Docker Desktop (optional) if you want to test agents locally in an isolated container sandbox that mirrors the cloud runtime.
  • A Charm account for publishing to the Store — sign up at store.charmos.io.

​
How it works

How it works

​
Start Here

Configuration

Define identity, inputs, runtime adapter, pricing, auth, and policies in a single charm.yaml manifest.

Run & Test

Execute your agent locally with charm run, or simulate the cloud environment in Docker with —docker.

​
Key Features

Secrets Management

Declare required API keys in charm.yaml. The Cloud Runner injects platform-managed secrets at runtime — no hardcoding needed.

OAuth

Require Google, GitHub, Notion, or Slack authorization. The Store prompts users to connect accounts and injects provider tokens into the runtime.

Ambient Desktop Companion

Run agents as native desktop companions with access to local files, hardware context, and persistent memory.

Server-Driven UI

Return structured JSON to render timelines, comparison tables, viral cards, and articles — zero frontend code required.

Payments

Set free, one-time, or subscription pricing in charm.yaml. Charm handles checkout, wallet balance, and creator payouts via Stripe.

​
Community & Resources

Charm Store

Browse and run published agents on the live storefront.

Contact Us

Reach the core team for partnership, support, or enterprise inquiries.

Discord

Join the community — get help, share agents, and discuss ideas with other builders.

Blog

Follow platform updates, feature announcements, and builder spotlights.