A URL for everything your open-source models make
Where humans and your open-source models
work on dashboards together.
You run the model. display.dev is where its output lands – one command, a URL that never changes, gated by your company's Google or Microsoft login.
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
Publishing self-hosted model output for your team
You chose an open-weight model for a reason: data stays on your infrastructure, no per-token vendor bill, no lock-in to one API. Llama, Qwen, DeepSeek, Mistral, gpt-oss – the model runs and it writes a competitive analysis, a dashboard, a research summary, an internal doc. Then someone has to read it.
display.dev closes that last mile: the output gets a URL, the URL is gated by company login, and anyone on the team can open it.
- ✗No hosted share buttonwhen the model is yours, no vendor offers one.
- ✗No account to sign intoyour PM, your exec, a teammate on another squad have a login for none of it.
- ✗A file on a serverit needs credentials nobody on the business side has.
- ✗Emailed, screenshotted, pasted into Slackinteractivity gone, and no stable reference.
Three ways to publish self-hosted output
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 AI account anywhere. Viewers sign in with the Google or Microsoft account they already use. Nothing to install, no model account, no display.dev account.
Change the model, keep every published URL
The open-weight leaderboard turns over every few months. You'll swap models – Llama to Qwen, a 70B to a fine-tune, one inference engine to another. Everything you published stays where it is: same URLs, same versions, same comment threads.
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
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.
dsp publish ./file.html from your terminal, or one MCP tool call from your agent. 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.
Llama, Qwen, DeepSeek, Mistral, gpt-oss – plus Cursor, Codex, Claude Code, or your own scripts.
Try it free
- Publish your model's output in under a minute, no card
- Keep the URL when you upgrade
- Unlimited viewers on every plan
Common questions.
Which open-source models does this work with?
All of them. display.dev publishes any HTML or Markdown file on disk – it never sees the model. Llama, Qwen, DeepSeek, Mistral, gpt-oss, Gemma, OLMo, Phi, or a fine-tune of any of them: if it writes a file, dsp publish works.
Do viewers need a display.dev account or any AI account?
No. Viewers sign in with their company Google or Microsoft email. No display.dev account, no model account, no API key on their side.
Does my model output leave my infrastructure?
Only the artifact you explicitly publish leaves – the HTML or Markdown file you run dsp publish on. Your model, weights, and inference stack stay entirely on your own hardware. display.dev hosts the published output, nothing upstream of it.
Can my inference pipeline publish automatically?
Yes. Call dsp publish at the end of your script, or wire display.dev's MCP/REST API into the agent so it publishes its own output and returns the URL. No human publishing step.
What if I switch models later?
Nothing moves. display.dev is independent of whatever produced the output, so swapping models leaves every URL, version, and comment thread exactly where it was.
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).