WebCLI — Agent Interface Device for the World Wide Web
×
Skip to content
Your agent just got its browser driver's license.
Let it take your web tasks for a spin.
You don't have to drive every web task yourself anymore. Tell your agent what you need done.
WebCLI is for contact with reality — when your agent must inspect an unknown page, decide what to do, act, recover from blockers, and pause for a human when the web needs one.
Start 5-day trial<br>Watch demos
Browser Driver's License<br>Issued by: WebCLI
NameAgent<br>ClassWeb<br>StatusLicensed<br>RestrictionsPause for human handoff when blocked
Drive responsibly. Automate wisely.
curl -fsSL webcli.sh/install.sh | bash<br>Copy
Signed releases. Works with local browser profiles. macOS, Linux, and Windows.
What if the browser was just another Unix command?
Open a page. Observe state. Pipe JSON through jq. Act on numbered refs. Leave a transcript.
The web, finally pipeable.No screenshot soup. No selector archaeology. Just commands, JSON, and a real browser.
web session
$web open https://example.com --json
{ "ok": true, "url": "https://example.com", "state": "complete" }
$web observe --json | jq '.actions'
["1: Sign in", "2: Create account", "3: email", "4: password"]
$web do 3 --json
{ "ok": true, "message": "clicked Sign in" }
$web status --json
{ "state": "blocked", "reason": "passkey confirmation required" }
$web pause "Need human approval for passkey"
Paused. Waiting for human to join.
$web transcript --last 20 --json
{ "events": ["redacted transcript with blocker, pause, and resume recorded"] }
Agents code. They even search. But the second they try to do something on the web, they go blind.
Real work still happens on websites: dashboards, portals, auth flows, admin pages, and changing UIs. WebCLI is for contact with reality — when an agent must inspect, decide, act, recover, and sometimes pause for human help.
Three clouds. One browser loop.
Agents drove Azure, AWS, and GCP through the browser.
No cloud SDK script. No prewritten Playwright flow. Just real cloud consoles, operated through WebCLI.
Full Self Browsing has been achieved.
▶ Play
Azure, AWS, and GCP<br>Three clouds. One browser loop.
Codex creates and deletes VMs across Azure, AWS, and GCP. No SDK scripts. No prewritten Playwright flows. Real cloud consoles, operated through WebCLI.
Azure Portal (Fluent UI, dynamic blades, VM creation)<br>AWS EC2 (regions, tables, modals, status)<br>GCP Compute Engine (projects, async ops, IAM)
Watch demo<br>Read report<br>YouTube
▶ Play
Login does not count. The race starts inside the console.<br>Three clouds. One race.
Claude drives GCP, AWS, and Azure VM creation in a race. Human auth is handoff. The race starts inside the console.
Human auth is handoff — race starts post-login<br>Same WebCLI loop on all three consoles<br>Verify creation, stop before high-risk choices
Watch the race<br>Read report<br>YouTube
▶ Play
Full cleanup run<br>Claude Sonnet deletes VMs across cloud providers.
Claude Sonnet deletes VMs across cloud providers through the browser loop — no cloud SDK, no hardcoded scripts, just WebCLI.
Works across different cloud UI systems<br>Same observe → choose → act loop throughout<br>Transcript records every step
Watch cleanup
YouTube
Web jobs. Zero scripts.
Ship a site. Wire up DNS.
Agents deploy Cloudflare Pages sites and configure DNS — through the browser portal, no CLI tools, no prewritten scripts.
▶ Play
Deploy · DNS · Live<br>Claude Haiku 4.5 deploys a site and wires up DNS.
Haiku 4.5 deploys a Cloudflare Pages site through the dashboard, then configures DNS through Namecheap — all through WebCLI. No wrangler. Portal only.
Cloudflare Pages deployment via portal<br>DNS configuration through Namecheap<br>Full session from zero to live
Watch demo
YouTube
▶ Play
WebCLI builds and deploys webcli.sh<br>Agent ships its own landing page.
A full session: Claude reads the spec gists, rewrites all site copy, builds the HTML, and deploys to Cloudflare Pages — then uploads this recording to YouTube. No wrangler. Portal only.
Reads spec from GitHub Gists<br>Rewrites copy, builds HTML, deploys via Cloudflare dash<br>Uploads session recording to YouTube mid-session
Watch demo
YouTube
Category: Interface Architecture
Humans get GUIs. Programs get APIs. Agents need TAIs.
WebCLI is a Textual Agent Interface for the browser: structured state, numbered actions, tabs, profiles, blockers, handoff, and transcripts.
The web has human interfaces. Now it has an agent interface. WebCLI translates messy live websites into the language agents already understand: observable state, numbered actions, browser context, blockers, and transcripts.
The browser was built for viewing. WebCLI is built for doing.
Pages become observable state.<br>Buttons and fields become numbered actions.<br>Tabs, frames, dialogs, popovers become inspectable browser surfaces.<br>Passkeys, MFA, file choosers, ambiguity become blockers and handoff.<br>Agent/browser history becomes redacted transcript.
The...