Browser Use Desktop App
-
Updated
Jul 1, 2026 - TypeScript
Browser Use Desktop App
Local replay debugger for Browser Use failures with screenshots, model I/O, failed-step timelines, and public-safe HTML exports.
Give your agent a reusable memory of web actions: learn a task once, then replay it deterministically.
Open-source Python framework for multi-agent AI orchestration, coding-agent swarms, council voting, provider routing, browser tools, MCP connectors, and workflow automation.
Make any web app agent-ready, verifiably — an agent skill that integrates WebMCP end to end: inventory, integrate, verify, heal.
Lightweight library that extracts actionable context from any website's DOM for AI browser agents and RPA workflows (3,000+ installs).
🤖 Ready-to-run Python examples for Browse Anything API. Automate web scraping, price monitoring, multi-step workflows, QA testing, and lead generation using natural language prompts.
A privacy layer for computer-use agents. Built by Jerry Gu, Trisanth Srinivasan, Zach Chen, Anantha Kandrapu, and Dael Amzalag.
Local first AI coding agent built for real software work.
Codex AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for openai/codex.
Browser-native recipes for agent workflows with clear inputs, outputs, guardrails, and demo-ready business value.
Agent Browser AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for vercel-labs/agent-browser.
MCP Playwright AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for executeautomation/mcp-playwright.
Agency Swarm AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for VRSEN/agency-swarm.
Evidence-first reliability for browser agents: classify UI drift, approval-gate adaptation, and roll back regressions
Make web UIs controllable by browser agents without brittle selectors.
Markfetch AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for vasylenko/markfetch.
Local-first observability for browser agents. See what your agent actually did.
aggregated collection of browser/computer use agent evals
MCP Chrome AI context pack for Claude Code, Codex, Cursor, and Aider: AGENTS.md, CLAUDE.md, prompts, evals, pitfalls, and verification notes for hangwin/mcp-chrome.
Add a description, image, and links to the browser-agents topic page so that developers can more easily learn about it.
To associate your repository with the browser-agents topic, visit your repo's landing page and select "manage topics."