MCP servers and skills: search, filter by where they run, and compare.
Browser compatibility and Baseline status for any web feature — offline, from MDN's browser-compat-data, web-features, and caniuse. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 1Few starsNo key
MCP server giving LLM agents a real desktop Chrome (X11 mouse, Cloudflare Turnstile auto-solve) via the browser-agent-server daemon. Companion project: vernikr/browser-agent
Node.jsMITFew starsNo key
Agent-first lightweight browser automation — direct CDP, no Playwright, more accurate and more reliable.
SkillMIT★ 54No key
MCPLink onlyFew stars
MCPLink onlyFew stars
Give any AI agent your real Chrome: token-cheap text perception, a visible cursor, MCP + HTTP API. Optional chat watcher.
Node.jsMIT★ 2Few starsNo key
Agent Skill for Codex, Claude Code, Cursor, GitHub Copilot, and OpenCode to build, test, and publish Chrome extensions.
SkillMIT★ 3Few starsNo key
Portable WPE WebKit runtime for AI agents with native input, screenshots, ordered JSONL, and reproducible benchmarks.
DockerApache-2.0★ 2Few starsNo key
Local browser-control engine for MCP agents: existing Chromium sessions, per-site permissions, one-use approvals, and isolated Playwright profiles.
Node.jsMIT★ 4Few starsNo key
Let your coding agent read your real, logged-in Chrome: MV3 extension + native host + MCP server (read_active_tab, open_and_read_url). Zero dependencies, MIT.
SkillMITFew starsNo key
Node.jsMITFew starsNo key
NexusBrowser: your real Chrome driven by AI agents (Antigravity, Claude, Codex) in background tabs, through a local bridge and an MCP server.
PythonMIT★ 4Few starsNo key
Open-source browser automation for Codex and MCP. Jev/Laya decisions, Playwright execution, Brave sessions, persistent extension authentication and verified workflows.
SkillMIT★ 4Few starsNo key
Browser use for coding agents, 3-5x faster than browser-use. MCP server + CLI; TypeSafe Jev decides every step in ~300 ms.
Node.jsMIT★ 4Few starsNo key
Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.
SkillMIT★ 51No key
Browser use & computer use for coding agents, powered by TypeSafe Jev: calibrated judgments from a System One model, control loop in code. ego lite / Chrome / Safari · CLI + MCP
SkillMIT★ 3Few starsNo key
Pause and safely resume Browser Use tasks at CAPTCHA: same-session detection, authorized handoff/test actions, and fresh validation. Local MCP + SDK.
Node.jsMIT★ 1Few starsNo key
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 m
PythonMIT★ 19No key
Your Chrome, now an agent browser. No browser switch. No login migration. Codex, Claude Code & more. Free & open source.
Node.jsMIT★ 9No key
Claude Code skill: a background Playwright browser for screenshots (desktop/tablet/mobile), frontend health checks, visual diffs, scripted UI flows and logged-in pages — in any project. ｜ 讓 Claude Cod
SkillMIT★ 51No key
Fast browser hands for coding agents: name an outcome, and Jev (TypeSafe's decision model) picks each click in about 300 ms. MCP server, Claude Code plugin, library and CLI; works in a browser it laun
Node.jsMIT★ 1Few starsNo key
MCP server that lets many Claude Code sessions and subagents share numbered, logged-in Chrome instances over CDP
Node.jsMIT★ 2Few starsNo key
MCP server that runs plain-language browser steps. Jev, a typed decision model, picks the control on each page instead of an LLM reading the DOM.
Node.jsMITFew starsNo key
Who stands behind it
