Documentation

Every Ghosty Studio agent is its own machine: disk, terminal and memory. Here is how to create one, where to put it to work, and how to talk to it from your software.

Which path?

I want an agent now
5 min
Create one, talk to it and connect a channel in five minutes.
→
Answer on WhatsApp
no code
Connect the number in Sales and turn on the channel on the card: voice notes, images, PDFs.
→
In my team (Teams)
no code
An @handle in your workspace: documents, forms, tasks and email.
→
From my editor
npx
Zed, VS Code or JetBrains talking to your agent over ACP.
→
From my own software
API
OAuth2 + REST API with streaming events. OpenAPI 3.1.
→
Configure it with my coding agent
npx skills add
Identity, files, skills and MCPs over an API; Claude Code or Cursor do it for you.
→

Full index

Getting started

Getting started
Create an agent, hand it a PDF and watch it download it to its machine, read it and answer with the exact figures. Ten minutes, no code.
Concepts
Agent, machine, conversation, turn, channel, connector, skill, engine and plan — the vocabulary of Ghosty Studio.
Configure your agent from your coding agent
Identity, model, knowledge files, skills and MCP servers — all through an API with the agent's token, plus a skill so Claude Code, Cursor or Codex do it for you.

Channels

WhatsApp
The number is connected in Sales (WhatsApp Business) and on the agent card you pick which numbers it answers; voice notes, images and PDFs.
Teams
Activate a Studio agent in a Ghosty Teams workspace with an @handle; channels, DMs, documents and tasks.
Embedded widget
Put a chat with your agent on your own site with an iframe. Available for EasyBits-engine agents.

Connectors

Connectors
External accounts the agent accesses on your behalf — Google, Canva, Spotify, Odoo, GitHub — and how they are connected.

Protocols

ACP — connect your editor
Connect Zed, VS Code, JetBrains or neovim to a Ghosty Studio agent over the Agent Client Protocol.
A2A — agent to agent
Every agent publishes an A2A v1.0 Agent Card so other agents can discover it; the message endpoint opens to third parties soon.
MCP — the agent's tools
What tools a Ghosty agent has, how they are named and how they reach each engine through the Model Context Protocol.

API

Authentication
OAuth2 with PKCE to talk to the Ghosty Studio API on behalf of a person — scopes, tokens, errors and how to get a client_id.
API reference
Every endpoint of /api/v2/me — agents, conversations, messages, events, permissions, files, connectors — with its OpenAPI 3.1 schema.
Events (SSE)
Catalog of a conversation's stream events — started, chunk, tool, permission, artifact, done — and how to write a client that doesn't miss anything.
Errors and limits
Response codes of the Ghosty Studio API, what each one means and how to retry; sizes and caps.

Reference

Changelog
What changed in the platform and in this documentation, by date.
Security
What isolates one agent from another, where your keys live, what an agent can do on a public channel and how an account is deleted.