h5i
h5i is a lightweight, policy-controlled browser for AI agents, built in Rust, that combines page automation with direct control over HTTP traffic. It solves the problem of giving agents a secure, auditable way to browse and interact with web pages, with sandboxing and network controls. It is for developers building AI agents that need to scrape, test, or interact with web applications securely.
✨ Key features
- Pure Rust, no Chromium or V8
- ~3× faster, ~86% less memory in benchmarks
- Sandboxed and auditable: browser-only or full workflow
- Built-in HTTP workbench: capture, edit, replay, diff
- Configurable isolation tiers: workspace to microVM
- Session recording with requests, audit, and status
🎯 Use cases
- Scraping content-heavy websites
- Automated web testing with multi-step flows
- Authorized red teaming and web security testing
- Running AI agents that build and browse apps in sandboxes
- Stealth-mode browsing with custom identities
📦 Installation
🧰 Requirements: Runs locally; optional rootless Podman for container isolation, microsandbox (msb) for microVM on hosts with /dev/kvm or Apple Silicon. No API keys required.
curl -fsSL https://h5i.dev/install.sh | sh
# curl -fsSL https://raw.githubusercontent.com/h5i-dev/h5i/main/install.sh | sh # if you would rather not add a domain to the chain:
# cargo install --path . # build from source
The agent-facing interface is a skill, and the binary carries it:
npx skills add h5i-dev/h5i # if you do not have the binary yet
# h5i skill install # writes it where your runtime looks
# h5i skill show policy # or just read a page
🚀 Usage
h5i browser open https://example.com
h5i browser snapshot # the page as a model should read it
h5i browser click @e3
h5i browser requests # what it asked for, and what was refused
h5i browser audit # the whole session: verbs, fetches, handovers, ending
h5i browser close
⚠️ Good to know
h5i does not work on every website; it works best for content-heavy sites and common interactions, but some browser APIs are not yet supported.
❓ FAQ
What is h5i?
h5i is a fast, lightweight browser for AI agents, with built-in auditing and configurable sandboxing. It runs locally and is open source.
Why use h5i instead of Playwright or Puppeteer?
Use Playwright or Puppeteer when maximum website compatibility is your priority. Use h5i when you need lower resource use, network controls, a complete session record, or a sandbox for both the browser and agent.
Does h5i work on every website?
No. h5i works best for content-heavy websites and common browser interactions, but some browser APIs are not yet supported. For incompatible websites, you can run Chromium inside an h5i sandbox.
Is h5i sandboxed by default?
The browser uses lightweight process isolation when available. For stronger isolation, place the browser, or the agent's entire workflow, inside a container or microVM.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.