display.dev for Ollama
Ollama runs the model locally. display.dev is where its output lands – at a permanent URL, behind your company login when you want it. Ollama binds to `localhost` by design – great for inference, but there's no path from a model-generated file to a URL your team can open. display.dev is that path. One command, permanent URL, gated by your company's Google or Microsoft login.
Ollama is local by design. Sharing isn't.
Ollama is the easiest way to run Llama, Qwen, DeepSeek, gpt-oss, or any open-weight model on your own hardware. It runs on 127.0.0.1:11434 and exposes an OpenAI-compatible API. Everything stays on your machine.
Then the model writes something worth sharing – an HTML report, a dashboard, a Markdown brief – and the local-by-default architecture works against you. The usual answers are tunnels (ngrok, Pinggy) and Open WebUI, but those expose a chat interface or a raw port, not a stable, company-gated home for a specific piece of output. The teammate who needs to read it has no account anywhere, because there's no vendor in the loop.
display.dev closes that gap without putting your model on the internet.
From Ollama output to a company URL
Publish a file the model wrote:
ollama run llama3.3 "Write an HTML competitive analysis" > report.html
dsp publish ./report.html --name "competitive-analysis"Publish from a script around the Ollama API:
python generate_report.py # calls localhost:11434, writes ./report.html
dsp publish ./report.html --name "report-$(date +%Y-%m-%d)"Publish as an agent tool call (MCP):
{
"name": "publish",
"arguments": { "content": "<html>...", "name": "ollama-output", "visibility": "company" }
}The URL is permanent and authenticated. Paste it in Slack. Your teammate signs in once with their company email and sees the full rendered page.
Viewers sign in with their work email. Nothing else.
Running models locally means there's no vendor with a "share with my org" button – which is exactly why you run them locally. It also means your viewers have no account to authenticate against.
display.dev is vendor-independent. Viewers sign in with the Google or Microsoft email they already use for work. No display.dev account to create, no Ollama install, nothing to set up. They click the link and read the page.
The best model changes. The home doesn't.
You'll ollama pull a new model next month – a fresh Qwen, a different fine-tune, a bigger gpt-oss. display.dev sits above the model. Swap what runs in Ollama freely; everything you published keeps its URL, versions, and 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: 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
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.
dsp publish ./file.html from your terminal, or one MCP tool call. 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.
Whatever Ollama is running – plus Claude Code, Cursor, Codex, or your own scripts.
Common questions.
Does this put my Ollama server on the internet?
No. display.dev hosts only the file you explicitly publish. Ollama stays on localhost; your models and weights never leave your machine. You're publishing the output, not exposing the server.
Do viewers need Ollama or any AI account?
No. Viewers sign in with their company Google or Microsoft email. Nothing to install, no model account, no display.dev account on their side.
Can I publish Markdown the model wrote, not just HTML?
Yes. dsp publish ./brief.md renders Markdown to a styled page. HTML and Markdown are both first-class.
Can my script publish automatically after inference?
Yes. Add dsp publish to the end of the script, or wire display.dev's MCP/REST API into your agent so it publishes its own output and returns the URL.
What happens when I switch the model in Ollama?
Nothing moves. display.dev is independent of what produced the output, so every URL, version, and comment thread stays put.
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).