Loading...
Loading...
AI-powered browser automation SDK for web scraping, testing, and workflow automation. Use when automating web browsers, extracting data from websites, testing web applications, or building web automation workflows. Supports both API key and AWS credential authentication.
npx skill4agent add amazon-agi-labs/nova-act-agent-skills nova-actexport NOVA_ACT_API_KEY="your_key"@workflowreferences/workflow_definitions.mdreferences/authentication.md| User wants to... | Route to |
|---|---|
| Explore a website interactively | |
| Build a coding agent with browser | |
| Write a repeatable test script | |
| Write a Python automation script | |
| Convert manual tests to automated | |
| Understand a codebase via its UI | |
| Reproduce a bug | |
| Iterate on / refine automation prompts | |
| Generate mock sites from real site recordings | |
| Deploy to production | |
pip install 'nova-act[cli]'
act browser execute "Go to https://example.com, find the pricing page, and extract plan names and prices" --session-id work
# If you need to observe current state:
act browser ask "What page am I on?" --session-id work
# If you need a zero-inference jump:
act browser goto https://example.com/specific-page --session-id workexecutegotoask--nova-arg--nova-arg max_steps=5 --nova-arg headless=true--helpIMPORTANT: Before running any browser command, ask the user whether they want headed (visible browser) or headless mode, unless they have already specified. Useor--headedaccordingly.--headless
⚠️ CRITICAL: NEVER kill Chrome or Chromium processes (e.g.,,pkill chrome,kill -9 $(pgrep chrome)). Nova Act manages its own browser lifecycle. Killing browser processes externally will corrupt session state and break automation. If a browser appears stuck, usekillall Google Chrometo check status, or start a new session.act browser sessions
💡 Localhost HTTPS Testing: When testing against a local HTTPS server (e.g.,), Chrome will reject self-signed certificates by default. Addhttps://localhost:8443to bypass this:--launch-arg=--ignore-certificate-errors --ignore-https-errorsbashact browser goto https://localhost:8443 --session-id dev --launch-arg=--ignore-certificate-errors --ignore-https-errors⚠️ Only usefor localhost development servers. For non-local URLs, valid certificates should be used unless you have a specific reason to bypass validation.--ignore-certificate-errors
references/browser_cli.mdfrom nova_act import NovaAct
with NovaAct(starting_page="https://example.com") as nova:
nova.act("click the first link on the page")
result = nova.act_get("What is the page title?")
print(f"Page title: {result.response}")references/qa_tests.mdpython --versionpip install 'nova-act[cli]'pip show nova-actplaywright install chromereferences/browser_cli.md| File | What It Covers |
|---|---|
| Browser CLI — commands, sessions, config, page exploration. Default for interactive work and agent tool-use. You MUST read the ENTIRE file — it contains critical CLI best practices, command decision guides, and example transcripts that are essential for correct usage |
| Script writing — QA testing with pytest/unittest, act() vs act_get(), schemas, assertion patterns |
| Deployment CLI — deploy workflows to AgentCore Runtime on AWS |
| API key vs IAM, session management |
| Workflow definitions with AWS CLI |
| Structured extraction with Pydantic |
| Human approval and UI takeover patterns |
| External tools (@tool decorator, MCP servers) |
| Remote browser via AgentCore |
| Direct Playwright page access, sensitive input, file downloads |
| Logs, screenshots, and video recordings |
| Understanding Nova Act trajectories |
| Visual reporting — post-session markdown reports from steps.yaml, snapshots, and screenshots |
| Gherkin testing — |
| Flow discovery — live app exploration → codebase mapping, developer onboarding docs |
| Bug reproduction — reproduce → capture evidence → export → regression test |
| Parallel sessions — run multiple browser sessions concurrently with subagents, chunking, session limits |
| Workflow refinement — analyze chain-of-thought, identify failure patterns, revise and validate browser automation workflows |
| Mock generation — generate static HTML mock sites from real site trajectories for fast, offline iteration |