A URL for everything your LangChain agents make
Where humans and your LangChain agents
work on dashboards together.
LangChain runs the agent. display.dev is where its output lands – one tool call, a URL that never changes, gated by company SSO.
The demo shows an agent publishing a doc to display.dev – from a chat or a terminal – then the team opening its URL, commenting, the agent publishing v2 at the same URL, and the doc being shared with someone outside the company.
Cursor, Codex, Claude Code – any agent that writes a file. Switch agents anytime – your URLs, versions and comments stay put.
Indigo Engineering
Where LangChain agent output goes after the run
You build with LangChain so the agent isn't tied to one vendor: swap the model, change the graph, reuse chains across teams. The run finishes and the agent has produced something worth reading – a research brief, a dashboard, a generated report. Then it's a string in a callback, a file on a worker, or text in a LangSmith trace, and every workaround drops something.
display.dev is the publish step – a tool your graph calls, not a workflow a human runs after.
- ✗Email or Slackno stable URL, no interactivity, re-sent every run.
- ✗GitHub Pagesneeds a git push, excludes anyone without a GitHub account.
- ✗Confluence or Notioncan't render the HTML agents produce.
- ✗Vercel or Netlifyneeds a deploy project, and SSO is a paid add-on.
Three ways to publish from a graph
python run_graph.py, no code change in the graph.Who can open it
A public URL, no sign-in. Free covers unlimited public links.
Named email addresses only. Useful for a client or a contractor you don't want to hand company sign-in to.
Anyone signing in with a verified company domain gets in – Google Workspace, Microsoft Entra ID, or a one-time password by email. Viewers are unlimited on every plan.
No model-vendor account anywhere. A model-agnostic framework has no vendor your readers already hold an account with. They sign in with the Google or Microsoft email they already use for work.
Change the framework, keep every published URL
You chose LangChain so you could keep changing what's underneath – models, graphs, even the framework itself. display.dev sits one layer above all of it. Rebuild the agent however you like; everything you published keeps its URL, versions, and comment threads.
What LangChain agents publish
- Scheduled report graphs
- A LangGraph flow that runs nightly, fetches the current version, and republishes to a stable URL with
short_idandbase_version. Stakeholders bookmark the link once. - Research agents
- Deep-research and synthesis outputs published straight to a team-accessible URL, no human copy-paste.
- Tool-building agents
- Agents that scaffold an internal tool or dashboard, then publish the output so non-engineers get a usable link.
- Human-in-the-loop reviews
- Published artifacts collect inline comments; the graph reads them via MCP, republishes the updated version, and resolves the thread.
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: 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: 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: 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: 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 the current version at the same URL, 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 its own 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, LangGraph, and any other framework that can make an HTTP request or call an MCP tool.
Try it free
- Publish an agent run's output in under a minute, no card
- Keep the URL when you upgrade
- Unlimited viewers on every plan
Common questions.
Does this work with LangChain and LangGraph?
Yes. Add a publish step as a tool in your chain or graph using display.dev's REST API or MCP. display.dev only sees the HTML or Markdown you publish, not the framework.
Do viewers need a LangChain or model-vendor account?
No. Viewers sign in with their company Google or Microsoft email. No display.dev account, no LangChain login, no model-vendor account.
Can the agent publish its own output without a human?
Yes. The publish call is just another tool. The agent invokes it at the end of a run and gets back a URL to include in its response or post to Slack.
Can a scheduled graph update the same URL each run?
Yes. Publish with the artifact's short_id and current base_version. The URL stays the same; bookmarked links show the latest version.
What if we move off LangChain 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 Pro (€49/month flat).