iframer doesn't just browse a website, it learns it: caching endpoints and creating "anchors" for its key elements, so the next visit is instant.
It also covers the basics: secure sessions, headed/headless modes, best-effort captcha solving.
Built for real engineering work, not one-off research, and the benchmarks below prove it.
Hard tasks: many pages, real finding-your-way
Everest → Gojo, 6 hops, find each link
login → sort → cart → checkout
GitHub: look + pull 4 facts
Shorter bar wins. Where the others dump a whole accessibility tree into the model’s context, iframer returns a capped, filtered snapshot, so on the GitHub page it spends 986 tokens where Playwright spends 19,906. See the full benchmark →
Runs locally. Works with Claude Code, Codex, any MCP agent.
What it does
Browser modes
iframer auto-selects and auto-escalates: headless → binary-headful. See architecture for how that decision actually works.
Installing the extension
Optional. This is what lets your agent drive a tab in your real, already-logged-in Chrome instead of a fresh browser window. Needs iframer-toolkit installed first (the command at the top of this page).
iframer install extension chrome. It prints a folder path and ends in /extension, something like .../node_modules/iframer-toolkit/extension. Copy that whole path.chrome://extensions and turn on Developer mode, the toggle is top right.Cmd+Shift+G first to get a "go to folder" box, on Windows paste straight into the address bar at the top of the picker.That's it, no token to paste, no config file. Click the icon to check: the dot next to "iframer" turns green once it finds the local server. Lost the folder path later? Run iframer extension path any time.
How it works
What's inside
Full breakdown of the daemon, the flow, and the stack: architecture. Everything an agent actually calls: agent docs.
Open source · MIT license · 2026