PyRank
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About

Browser Automation Python Packages

Python packages with the GitHub topic browser-automation. Sorted by relevance, with stars and monthly downloads.
browser-use
browser-use

๐ŸŒ Make websites accessible for AI agents. Automate tasks online with ease.

203.2M 103K 11K
CloakHQ
cloakbrowser

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

542K 28K 2K
browser-use
browser-harness

Browser Harness | Self-healing harness that enables LLMs to complete any task.

326K 16K 1K
scrapfly
scrapfly-sdk

Official Python SDK for the Scrapfly platform: web scraping, screenshots, AI extraction, crawling, and a remote anti-bot browser. Integrates with Scrapy, LlamaIndex, and LangChain.

191K 59 15
steel-dev
steel-sdk

The official Python library for the Steel API

107K 34 5
pearjelly
cliany-site

A browser automation-to-CLI framework. Leveraging browser-use, LLMs, and the CDP protocol to automate the entire workflow: exploration, code synthesis, and execution.

12K 8 0
aadya940
orbit-cua

Building Blocks to automate desktop workflows end-to-end using AI

12K 6 0
ywatanabe1989
scitex-browser

Browser automation for scholarly research paper access

10K 0 0
afkbot-io
afkbotio

Local AI agent runtime and CLI with memory, MCP, browser control, automations, and subagents.

9K 3 0
flytohub
flyto-core

The open-source execution engine for AI agents. 412 modules, MCP-native, triggers, queue, versioning, metering.

9K 364 63
ginkida
sallyport

A security-first bridge between Claude Code (MCP) and Chrome โ€” HMAC pairing, domain allowlist, per-domain evaluate opt-in.

8K 5 1
Evil-Bane
eyebrowse

Stealthy, LLM-drivable browser-control engine: a Python library + an 85-tool MCP server on stealth Chromium (CloakBrowser) with full Chrome DevTools Protocol - for Claude Code and any MCP client.

8K 0 0
mentiora-ai
mentiora-loom

Agent-first browser automation runtime โ€” deterministic Chromium sessions with replay-equal hash chains, MCP-native tools, and a content-addressed action store.

6K 1 1
synacktraa
browser-handoff

Human-In-The-Loop for your browser-use agents.

6K 2 1
MathiasPaulenko
bidiwave

Python library for WebDriver BiDi communication with any browser. Async-first, cross-browser, no Selenium, no CDP.

5K 0 0
eracle
linkedin-agent-cli

Drive LinkedIn from the CLI or any program โ€” search, scrape profiles, check status, connect & message โ€” via a real browser session (Playwright) + the Voyager API. JSON-first, LLM-agent friendly. No API key, no SaaS.

5K 7 3
jumodada
drissionpage-mcp

DrissionPage MCP Server ยท Browser automation for Claude Code, Codex, and MCP clients

5K 127 5
WhyY0u
funbrowser

Undetect / anti-detect browser SDK for Python โ€” drives real Chrome via CDP with stealth patches, fingerprint customization, full proxy support, and automatic captcha solving (Turnstile, reCAPTCHA, hCaptcha, FunCaptcha) via funsolver.com.

5K 2 1
trueoriginlabs
vibatchium

Stealth browser automation for AI agents โ€” clears Cloudflare, one MCP server + N parallel persistent Chromes, credential vault, vision clicking, prompt-injection safety. 31/31 sannysoft, 594 tests.

5K 3 0
tsaijamey
frago-cli

Multi-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.

4K 60 12
LeonTing1010
taprun

Local-first browser automation MCP for Claude Code / Cursor. taprun compiles once with AI, your authenticated Chrome replays forever at zero LLM tokens. Credentials never leave your machine.

4K 10 0
arman-bd
chromiumfish

A stealth Chromium build with a drop-in Playwright harness for Python and Node, featuring natively built agentic capabilities.

4K 83 7
wronai
curllm

curllm - Intelligent browser automation with local LLMs (Qwen, Llama, Mistral) for data extraction and form automation using a dynamic LLM-DSL architecture without hardcoded selectors.

4K 3 2
ghostcrawl
ghostcrawl

Authentic, reliable web data at scale โ€” real Chrome, Firefox & WebKit browsers in the cloud. Crawl, scrape, extract & automate via API, SDKs, and MCP. Self-host free or use the managed cloud.

3K 0 0
    • Data from PyPI, GitHub, ClickHouse, and BigQuery