# hyperbrowserai/HyperAgent

AI Browser Automation

Repository: https://github.com/hyperbrowserai/HyperAgent
Canonical: https://ross.abutalabs.com/products/hyperagent
Homepage: https://www.hyperbrowser.ai/
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: ai, automation, playwright, llm, agent, chrome, web
Last push: 2026-05-11T21:41:09+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 81, release rhythm 25, longevity 36
- inputs: {"age_days": 506, "days_push": 114, "days_rel": 288, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1540, forks 198 (observed 2026-08-28T04:05:00.456936+00:00)

## What it is
HyperAgent is a TypeScript library and CLI that adds LLM-powered natural language commands to Playwright for browser automation. It supports AI task execution, data extraction, stealth anti-bot patches, action caching, and cloud scaling via Hyperbrowser.

## Use cases
- automate browser tasks with natural language instead of brittle scripts
- extract structured data from web pages using AI
- scrape websites while avoiding bot detection
- record and replay browser workflows without LLM calls
- run web automation tasks from the command line
- connect browser automation to external tools via MCP

## When to choose
- you want AI-driven browser automation on top of Playwright
- you need to extract data from sites with anti-bot protections
- you want to mix deterministic Playwright code with LLM-driven steps
- you need scalable headless browser sessions in the cloud

## When to avoid
- you need simple deterministic scraping without LLM costs
- you require a non-JavaScript/TypeScript stack
- you need a GUI-based automation recorder
- your project requires a permissive standard open-source license

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, web-scraping, llm-inference, cli, workflow-automation
- domain: artificial-intelligence, web-development, developer-tools, crawlers
- platform: cli, cross-platform
- tags: browser-automation, playwright, ai-agent, stealth-browsing, mcp-client, typescript, automation, ai-agents, nodejs

## Member repositories
- hyperbrowserai/HyperAgent (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:00.456936+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:51.047902+00:00, confidence not recorded.
  - readme: https://github.com/hyperbrowserai/HyperAgent (fetched 2026-08-28T04:05:00.456936+00:00, sha b378ed82b778)
  - homepage: https://www.hyperbrowser.ai/ (fetched 2026-08-29T11:32:24.071064+00:00, sha c5a83f73a1bb)
- Data as of 2026-08-30T08:39:29.467469+00:00.