Browser Agent Python Packages

browser-harness

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

stagehand

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

stagehand-py

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

fastbrowse

A fast browser agent: Jev picks each action from what is on the page, an LLM reads and plans, and every claim in an answer cites a quote from the page.

celesto

Secure and persistent computer for AI agents

celesto-core

Secure and persistent computer for AI agents

smolvm-core

Secure and persistent computer for AI agents

jev-ultrafast-mcp

Hand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model macro replay, over the Chrome DevTools Protocol.

wev-ai

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

terx

Browser-agent memory that turns repeated workflows into deterministic replays.

clawbench-eval

Open-source benchmark for browser AI agents on daily tasks.

openbrowse

The open-source Browser Use Cloud alternative: self-host AI browser agents on a Raspberry Pi or any server, same SDK, lower cost, visual-first.

stagehand-alpha

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

aether-browser

See what your agent sees. Self-hosted Chrome for AI agents with bounded API control, live noVNC takeover, npm/PyPI clients, and MCP servers.

waystone-browser

Browser action recorder for automation: record a task once, replay it, or hand the folder to an agent

openjev-ai

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisions and browser-agent steps.

perceive

Reachability-filtered perception layer for AI browser agents.

browsertrace

Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.

webqa-agent

Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent，支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估

agentwatcher

React DevTools for browser AI agents. Translucent overlay on every tab shows your agent's goal, last action, and next action — live, framework-agnostic.

harness-bench

Benchmark for comparing agent harnesses on everyday online tasks — fixes the base model, varies the harness. Sister project of ClawBench, same scoring pipeline.

uzdabrawza

The Anal-Queen of AI Browser Automation 🏴‍☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.

clawbench-harness

Open-source benchmark for browser AI agents on daily tasks.

claw-harness

Open-source benchmark for browser AI agents on daily tasks.