web-browser
Web Browser (agent-browser + Lightpanda)
Use agent-browser CLI via exec for all web browsing tasks.
Default engine: Lightpanda (fast, low-RAM). Falls back to Chrome if needed.
Quick Reference
Open a page
agent-browser open https://example.com
Get page content (text snapshot)
# Full content with text (for reading pages)
agent-browser snapshot
# Interactive elements only (for finding buttons/links/inputs to click)
agent-browser snapshot -i
# Structure only, no text (for understanding page layout)
agent-browser snapshot -c
# Scoped to a CSS selector
agent-browser snapshot -s "#main-content"
Interact with elements
Snapshots return refs like @e1, @e2. Use them to interact:
agent-browser click @e3 # Click a link/button
agent-browser fill @e5 "text" # Fill an input field
agent-browser type @e5 "text" # Type without clearing
agent-browser select @e7 "value" # Select dropdown option
agent-browser press @e5 Enter # Press key
agent-browser hover @e2 # Hover
agent-browser scroll @e1 # Scroll to element
Navigation
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser open <new-url> # Navigate to new URL
Typical Workflow
exec("agent-browser open https://example.com")- open pageexec("agent-browser snapshot")- read page content- If need to interact:
exec("agent-browser snapshot -i")- get interactive elements with refs exec("agent-browser click @e3")- click elementexec("agent-browser snapshot")- check result
Engine Selection
# Lightpanda (default, fast, low RAM, no screenshots)
agent-browser --engine lightpanda open https://example.com
# Chrome (fallback for complex sites or screenshots)
agent-browser --engine chrome open https://example.com
agent-browser screenshot # Only with Chrome engine
agent-browser screenshot --annotate # Annotated screenshot
Use Chrome engine only when Lightpanda fails on a complex site or you need a screenshot.
Notes
- Lightpanda: no screenshots, no visual rendering, but 10x faster and 10x less RAM
- Refs (
@e1) persist across exec calls — daemon stays alive between commands snapshot— full text for reading;snapshot -i— refs for clicking;snapshot -c— layout only- Google and some sites block headless browsers from cloud IPs (empty page) — use web_search instead
- If a site crashes with Lightpanda, retry with
--engine chrome
More from codealive-ai/ai-cofounder
exa-code-search
Code search using Exa. Finds real code snippets, API docs, and examples from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.
2exa-people-research
People research using Exa search. Finds LinkedIn profiles, professional backgrounds, experts, team members, and public bios. Use when searching for people, finding experts, or looking up professional profiles.
2strategic-review
Deep multi-phase strategic review of a specific decision — premise challenge, alternatives, risk map, adversarial review. Use for big choices (wedge, pricing, channel, hire, pivot). For quick framework lookup, use decision-playbook. For diagnosing why something is broken, use business-investigation.
2enterprise-sales
Help users navigate enterprise sales. Use when someone is closing large deals, managing complex buying committees, handling procurement, or converting PLG users to enterprise contracts.
2daily-recap
End-of-day consolidation — summarize daily log, promote durable facts to MEMORY.md, identify open threads
2launch-marketing
Plan and execute general product launches — PR outreach, GTM campaigns, buzz generation. For Product Hunt specifically, use product-hunt-launch (specs/tactics) and ph-launch-timeline (30-day prep plan) instead.
2