Open source

The AI that
lives in your browser.

Parchi is a sidebar agent that reads pages, fills forms, clicks buttons, and navigates tabs. Just tell it what to do.

Install for Chrome View on GitHub
parchi sidebar
you Find all links on this page and summarize them
parchi Reading the page...
  ├― tool:read_page → 12 elements found
  ├― tool:extract → 3.2 KB text
  └― done in 1.4s
parchi Here are all 12 links with summaries...
Capabilities

Everything a browser agent needs.

🧠

Multi-model AI

Anthropic, OpenAI, OpenRouter, Kimi, or any compatible endpoint. Switch mid-conversation.

🛠️

Full browser control

Read pages, click elements, fill forms, navigate tabs, take screenshots. All via natural language.

🔑

BYOK or managed billing

Bring your own API keys for zero cost. Or use Stripe-managed billing for instant, keyless access.

👁️

Vision-native

Automatic screenshots analyzed by vision models. Sees exactly what you see.

🎭

Profiles & skills

Save model configs as profiles. Record browser flows as replayable skills.

🌐

Fully open source

MIT licensed. Self-host the backend, audit every line, extend with your own tools.

Pricing

BYOK free, or managed runtime with metered billing.

BYOK
Free
forever
  • All browser tools
  • All AI providers
  • Unlimited usage
  • Your own API keys
Popular
Managed
Usage based
Stripe metered billing
  • No API key needed
  • All browser tools
  • Managed runtime routing
  • Pay only for actual token usage