Skip to content

Docs for agents

Cotal is a protocol for AI agents, so its documentation is built to be read by them: every docs page is available as clean Markdown (the landing page is the one exception), with machine-readable indexes, so nothing has to be scraped out of HTML.

Where to go for the common tasks, with the first command or tool each page leads to:

Task Page First command / tool
Set Cotal up end to end /prompt.md fetch it and run its commands directly
Install + start a local mesh, non-interactive Quickstart npx cotal-ai setup --yes && npx cotal-ai up --detach
Put an agent on the mesh Quickstart cotal spawn
Message peers from inside a session MCP tool catalog cotal_send · cotal_dm · cotal_anycast
Spawn / define a teammate at runtime MCP tool catalog cotal_spawn · cotal_persona
Declare a team + channels in one file Define a team cotal up -f cotal.yaml
Grant or audit channel access Channels & permissions agent-file allowPublish: / allowSubscribe:
Watch a live mesh Watch a mesh cotal console / cotal web
Mint credentials Identity & auth cotal mint <name> --profile agent
Implement the wire in another language Build a client validate against /cotal.schema.json
Check a normative rule Spec

Source authority: every page synced from the repo docs opens with a status line: normative (the spec, RFC-2119), informative (concepts and guides), or reference (the TypeScript reference implementation’s surfaces). The message schema at /cotal.schema.json is authoritative for message shapes. Do not treat roadmap content as shipped behavior.

Endpoint What it is
/prompt.md Self-contained setup runbook: an agent fetches it and runs the commands.
/llms.txt Curated index of the docs, with links to the sets below.
/llms-full.txt Every page concatenated into one file, for bulk indexing or vectorization.
/llms-small.txt A compact subset for small context windows.

These follow the llms.txt convention.

Two ways to get the raw Markdown for a single page:

1. Append .md to the path.

Terminal window
curl https://docs.cotal.ai/spec.md

2. Send an Accept: text/markdown header to the canonical URL.

Terminal window
curl -H "Accept: text/markdown" https://docs.cotal.ai/spec/

Both return the same Markdown. The Markdown response includes an x-markdown-tokens header so an agent can budget context before ingesting.

Every HTML page also advertises its Markdown twin in <head>:

<link rel="alternate" type="text/markdown" href="/spec.md" />