display.dev for agent platforms
Your platform runs the agent. display.dev is where the agent's output lands – at a permanent URL, behind your company login when you want it. LangChain, LangGraph, CrewAI, AutoGen, n8n, Goose, OpenHands, or an agent you built yourself – these frameworks orchestrate agents across any model. What they don't ship is a hosted place to put the HTML and Markdown those agents produce, where the right people can open it without an account. display.dev is that place: one tool call, permanent URL, gated by company SSO.
Your agent produces output. The platform doesn't host it.
Agent frameworks are built to be model-agnostic. You wire up a graph, a crew, or a workflow, and it runs against whichever model you point it at. That flexibility is the reason you chose a framework instead of one vendor's closed agent.
But the framework stops at the output. The agent finishes a report, a dashboard, a research brief – and now it's a string in a log, a file on a worker, or an attachment in an email. There's no built-in "publish this so my team can open it."
Every workaround leaves something out:
- Email/Slack: no stable URL, no interactivity, re-sent every time
- GitHub Pages: needs a git push, excludes anyone without a GitHub account
- Confluence/Notion: can't render the HTML agents produce
- Vercel/Netlify: needs a deploy project, paid add-on for SSO
display.dev was built to be the publish step – a function the agent calls, not a workflow a human runs after.
From agent output to a company URL
Via MCP (for MCP-compatible agents):
{
"name": "publish",
"arguments": {
"content": "<html>...",
"name": "research-brief-2026-w22",
"visibility": "company"
}
}
// → { "url": "https://acme.dsp.so/0kzNYG7O-research-brief-2026-w22" }Via REST API (any framework, any language):
curl -X POST https://api.display.dev/v1/publish \
-H "Authorization: Bearer $DISPLAY_TOKEN" \
-H "Content-Type: application/json" \
-d '{"content": "<html>...", "name": "research-brief", "org": "yourco"}'Via CLI at the end of a run:
dsp publish ./output.html --name "run-$(date +%Y-%m-%d)"The returned URL is permanent and authenticated. Anyone with a company email opens it; everyone else is blocked.
Viewers sign in with their work email. Nothing else.
A multi-vendor agent platform is, by design, not tied to any one AI company. That's the strength – and the reason there's no shared place for output. The colleague who needs to read the agent's report has no account with whatever model ran underneath, because there's no single vendor in the picture.
display.dev is vendor-independent. Viewers sign in with the Google or Microsoft email they already use for work. No display.dev account, no platform login, nothing to install. They click and read.
The best agent changes. The home doesn't.
You picked a framework so you could swap models, swap orchestration, and rebuild agents as the field moves. display.dev sits one layer above all of that. Rotate models, migrate from one framework to another, rewrite the agent entirely – everything you published keeps its URL, its versions, and its comment threads.
The agent is replaceable. The home for its work isn't.
What teams actually ship
- Scheduled-report crews
- A CrewAI or LangGraph flow that runs nightly, fetches the current version, and republishes to a stable URL with
short_idandbase_version. Stakeholders bookmark the link once. - Workflow output
- An n8n or Dify workflow that builds an HTML report at the end of a run and publishes it instead of emailing a fresh copy each time.
- Research agents
- Deep-research and synthesis outputs published straight to a team-accessible URL, no human copy-paste.
- Internal agents
- The agent you built in-house, publishing its own output to a company-gated URL so non-engineers get a usable link without touching a terminal.
Pricing
Try it. No credit card.
- Included: 10 gated artifacts
- Included: Unlimited public artifacts*
- Included: 50MB storage
- Not included: Version history
- Not included: Google + Microsoft SSO
- Not included: Private artifacts
- Not included: Audit logs
display.dev branded
Individuals. Unlimited gated sharing.
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: 1GB storage
- Included: 10 versions
- Not included: Google + Microsoft SSO
- Not included: Private artifacts
- Not included: Audit logs
For teams that need company auth.
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: 25GB storage
- Included: 50 versions
- Included: Google + Microsoft SSO
- Included: Private artifacts
- Included: 90 days audit logs
For compliance-driven organizations.
From $499/mo
- Included: Unlimited gated artifacts
- Included: Unlimited public artifacts
- Included: Custom storage
- Included: Unlimited versions
- Included: Google + Microsoft SSO
- Included: Private artifacts
- Included: 365 days audit logs
No per-API-call charges. No per-publish charges. No per-viewer charges. Flat.
Features
Viewers click a link and sign in with their Google or Microsoft account, or a one-time password. No app to install. No account to create. No IT ticket.
Inline comments on every artifact. Your agent reads them via MCP, fetches the current version, republishes with short_id and base_version, and resolves the thread. The artifact stays a living document, not a one-shot screenshot.
One MCP tool call, one REST request, or dsp publish ./file.html. No git repo, no deploy pipeline, no project to configure.
Every artifact gets a URL that keeps working. Share in Slack, link in Notion, paste in email. It still works six months later.
No per-seat pricing at any tier. Share with your PM, exec, legal team, or designer for the same flat price.
LangChain, CrewAI, AutoGen, n8n, your own agent – anything that can make an HTTP request or call an MCP tool.
Common questions.
Which agent platforms does this work with?
Any that can make an HTTP request or call an MCP tool. Natively via MCP: any MCP-compatible client. Via REST API: LangChain, LangGraph, CrewAI, AutoGen, n8n, Dify, Goose, OpenHands, or a custom agent in any language. display.dev only sees the HTML or Markdown you publish, not the framework.
Do viewers need an account on my platform or with the model vendor?
No. Viewers sign in with their company Google or Microsoft email. No display.dev account, no platform login, no model-vendor account.
Can the agent publish its own output without a human?
Yes. Wire display.dev's MCP or REST API into the agent. It publishes at the end of a run and returns the URL to include in its final response or post to Slack.
Can a scheduled agent update the same URL each run?
Yes. Publish with the artifact's short_id and current base_version. The URL stays the same; viewers who bookmarked it see the latest version.
What if we migrate to a different framework later?
Nothing moves. display.dev is independent of the framework, so everything you published keeps its URL, versions, and comment threads.
Publish your first artifact in 15 seconds.
Free tier. No credit card. One-time password auth on free, Google + Microsoft SSO on Teams ($49/month flat).