Codex runs the code. display.dev is where the output lands — behind your company login, at a permanent URL. One command. Authenticated URL. Your team can see it in 15 seconds.
OpenAI Codex — whether you're using the Codex CLI, the API, or the sandbox — generates real output: data analysis reports, web tool prototypes, interactive HTML visualizations, scraper results rendered as dashboards.
That output is local. There's no built-in path from a Codex-generated HTML file to a company-restricted URL.
The workarounds are the same as always: screenshot (loses interactivity), Slack upload (downloads as a file), GitHub Pages (excludes non-engineers), Vercel (requires a git project, $320/month for SSO).
None of them fit the Codex workflow. display.dev does.
Direct publish:
dsp publish ./analysis.html --name "weekly-analysis"In a Codex pipeline:
codex run analysis.py --output ./report.html
dsp publish ./report.html --name "analysis-$(date +%Y%m%d)"Via agent tool call (MCP):
{
"tool": "publish",
"params": {
"content": "<html>...",
"name": "codex-output-2026-w15"
}
}The URL is permanent. Paste it in Slack or email. Your team clicks it, authenticates with their company email once, and sees the full interactive result.
| Codex output | Use case |
|---|---|
| HTML data analysis report | Share with stakeholders without a BI tool |
| Interactive visualization | D3, Chart.js, Plotly output from a data run |
| Web tool prototype | Internal tool built with Codex agent |
| Scraper output dashboard | Competitive monitoring, market data |
| Multi-file static app | dsp publish ./output/ |
Any HTML that Codex writes to disk. display.dev serves it as a rendered page, not a download.
When Codex runs autonomously — generating reports, building tools, producing analysis — it can publish its own output via display.dev's MCP tool.
The agent invokes the publish tool with the HTML content and a name. display.dev returns a company-gated URL. The agent includes the URL in its final response or posts it to Slack.
No human in the loop for publishing. The output arrives at a permanent, authenticated URL automatically.
This is the agentic publishing primitive: agent produces content → content is immediately accessible to the right people → no sharing step required from the engineer.
Free — one-time password auth, 50MB, unlimited viewers
Pro ($49/month) — Google + Microsoft SSO, 25GB, custom domain, unlimited viewers
Publish your first Codex artifact free →
Authentication. 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.
Comments. Inline comments on every artifact. Your agent reads them via MCP, updates the document, resolves the thread. The artifact stays a living document, not a one-shot screenshot.
Publish in 15 seconds. dsp publish ./file.html from your terminal, or one sentence in Claude Desktop. No git repo, no deploy pipeline, no project to configure.
Permanent URLs. Every artifact gets a URL that keeps working. Share in Slack, link in Notion, paste in email. It still works six months later.
Unlimited viewers. No per-seat pricing at any tier. Share with your PM, exec, legal team, or designer for the same flat price.
Any agent. Claude Code, Codex, and Cursor all work, along with anything else that creates HTML or Markdown output. Not locked to one provider.
Yes. display.dev's CLI publishes any HTML file on disk — it doesn't care which tool generated it. For programmatic publishing from the Codex API, use display.dev's REST API or MCP tool.
Yes. Configure display.dev as an MCP tool in your Codex agent setup. The agent invokes the publish tool and receives a URL to include in its response or post elsewhere. No manual step required.
No. Viewers authenticate with their company Google or Microsoft email. No OpenAI subscription required.
Run dsp publish ./output/ to publish the entire directory. display.dev serves index.html at the root and resolves all relative asset references.
Free tier. No credit card. One-time password auth on free, Google + Microsoft SSO on Teams ($49/month flat).