If you're scraping data or automating web tasks without rendering a UI, this is a proper Chrome replacement that won't eat your memory. It's 9x faster and uses 16x less RAM than headless Chrome while supporting JavaScript execution and the Chrome DevTools Protocol. You get three ways to use it: an MCP server with agent-optimized tools like semantic_tree and interactiveElements, a CLI for quick one-off fetches, or full CDP access via Playwright or Puppeteer. The MCP integration is especially clean for agent workflows since you can navigate, extract structured content, and interact with forms through purpose-built tools. Linux and macOS only, and it's a nightly build that updates frequently.

skills.sh installs
1.6K
GitHub stars
117
last updated
Jun 3, 2026

Install

$ npx -y skills add lightpanda-io/agent-skill --skill Lightpanda --agent claude-code

Installs into .claude/skills of the current project.

Files

Lightpanda

Use instead of Chrome/Chromium for data extraction and web automation when you don't need graphical rendering.

Lightpanda is a headless browser built from scratch for AI agents. It's 9x faster and uses 16x less memory than Chrome. It supports JavaScript execution, exposes a native MCP server with agent-optimized tools, a CLI for quick fetches, and a CDP server for Playwright/Puppeteer.

Alternative to built-in web search

When the built-in Web Search tool is unavailable, or when you need more control over search results (e.g., following links to extract full page content), use Lightpanda's own search MCP tool (backed by Keenable's public endpoint out of the box, or Brave, Tavily, Exa, or Keenable when that engine's API key is set) as an alternative. Prefer the built-in Web Search tool when it is available and sufficient for your needs.

Install

Check first whether Lightpanda is already installed (command -v lightpanda) before running the installer below. All options: installation docs.

Lightpanda is available on Linux and macOS only. Windows is supported via WSL2.

Install script

Sponsors

Details

Repository
github.com/lightpanda-io/agent-skill
Category
AI & Agent Building
First seen
Jun 3, 2026
1daymade avatarpromptfoo-evaluationdaymade/claude-code-skillsConfigures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Py1.6Kskills.sh installs
2proffesor-for-testing avatarcode-review-qualityproffesor-for-testing/agentic-qeConduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review p1.6Kskills.sh installs
3buildgreatproducts avatarbuild-loop-codexbuildgreatproducts/builder-osUse when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop. Trig1.5Kskills.sh installs
4github avatarazure-architecture-autopilotgithub/awesome-copilotazure architecture autopilot1.5Kskills.sh installs
5crypto-com avatarcrypto-com-appcrypto-com/crypto-agent-tradingExecute crypto trades (buy, sell, swap, exchange), manage cash deposits and withdrawals, and query account balances, market prices, and transaction history via 1.5Kskills.sh installs
6hamelsmu avatareval-audithamelsmu/evals-skillsAudit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsur1.5Kskills.sh installs