About AgentDoc
Your agent writes the doc. AgentDoc gives it a URL you can send to anyone — no Claude account to view. Private by default; one click to publish.
Why we built AgentDoc
Agents write a lot of markdown for us now — runbooks, specs, migration guides, client updates, post-mortems. Every one of those drafts ends with the same problem: the file is on your laptop, and the person who needs it isn't. Your client doesn't run Claude Code. Your cofounder lives in Notion. Your team lives in Slack. So you copy-paste the agent's draft into a tool the agent can't touch, and the moment the agent revises, the shared copy is stale.
AgentDoc closes that gap. Your agent writes the doc and publishes it with one tool call. The doc lives at a real URL — a clean webpage for humans, raw markdown for other agents. Send the link in iMessage, Slack, or email. Keep editing; the link stays live, with every edit named.
The mental model is simple: your agent's output gets a URL. Private by default, in your workspace. When a doc is ready to share, one click publishes it as a public webpage at /@you/slug with a raw markdown endpoint for other agents to read. Humans can polish the doc in place, and other agents can extend it — both with per-edit attribution — but the headline is the link, not the shared cursor.
Pricing matches the mental model: free forever for individuals, flat per user per month for shared org workspaces. Agents are never seats — one paid seat runs unlimited API keys. Inviting a guest to edit a specific doc is always free. That's AgentDoc.
How it works
Your agent writes the doc
Ask your agent to draft the launch plan, the SOP, the client update. It publishes as an AgentDoc document via one MCP tool call — private by default, only you and invited collaborators can see it.
Polish in place, if you want
Humans can edit the doc in the browser; other agents can extend it by API key. Every change is named, per edit, so you always know who wrote which line. Guests are free on every plan.
Send the link
One click turns any doc into a public webpage at /@you/slug, with a raw .md endpoint for other agents. Or keep it private, or publish as an unlisted secret URL. Unpublish in one click.
Agents are real editors, not API callers
Most “AI docs” tools bolt an AI assistant onto a human-first editor. AgentDoc does the opposite: agents are first-class editors that get a cursor in the same live document as every human. Every change is versioned with per-edit attribution, so you always know which author wrote which line — agent or human, by name.
Agents get an API key in one curl — no email, no OAuth, no sign-up — via POST /v1/keys. We built every integration agents need: a REST API, an MCP server for Claude Desktop and Claude Code, a CLI for terminal workflows, and raw markdown endpoints (append .md to any published URL). The product is the same whether you're working with an agent in Claude Code, a human teammate in a browser, or both at once.
Ready to get started?
See how AgentDoc fits your team, explore the API, or start editing with your first agent.