An AI-assisted recruiting workflow for defining roles, finding and screening candidates, reviewing talent markets and resumes, arranging interviews, and maintaining hiring records.
Generate NotebookLM artifacts (slides, audio, video, mind maps, quizzes, flashcards, infographics, reports, data tables) from your notebooks. Use when the user wants to create any NotebookLM Studio output from their uploaded sources.
★not rated 65 1mo agoA
tokens not measured
originalMIT
Give your AI agent eyes and hands on your live Chrome browser and Electron apps — screenshots, DOM inspection, form automation, console monitoring, all via CDP.
★not rated 22
changed 8d agoA
tokens not measured
forkMIT
Run and debug a live app from inside Claude Code: breakpoints and variable inspection in Chrome and Node.js, managed dev servers, and replayable call history so setup is never re-driven by hand.
★not rated 17▲
+1 7d agoA
tokens not measured
originalMIT
A shared Chrome browser (human + Claude, CDP + Playwright MCP) that learns how each site is navigated: the human drives with the mouse and clears captchas/logins, Claude operates over CDP, and tandem:map persists per-site navigation memory (durable locators, drift, auto-injection).
★not rated 12 3mo agoA
tokens not measured
originalMIT
Drive a running Coherent Gameface UI from your coding agent (Claude Code, Codex CLI): ships the gameface-devtools-mcp server (evaluate JS, screenshot, inspect and drive the DOM, capture the console, set JS breakpoints over a direct Chrome DevTools Protocol connection), plus skills.
★not rated 7
changed 15d agoA
tokens not measured
originalMIT
A browser companion for AI assistants. Bundled MCP tools for Chrome automation, persistent project memory (Continuum chain), and an in-page hint modal — pair with the Mochi Chrome extension.
★not rated 3 2d agoA
tokens not measured
originalMIT
Web search, read and research through a real stealth-patched Chrome. Text hidden from human readers is stripped before the model reads it and reported, every source carries a SHA-256 provenance receipt, and the SSRF guard is re-checked after redirects.
★not rated 1
changed 10d agoA
tokens not measured
originalMIT
An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.
★not rated 0 2mo agoA
tokens not measured
originalMIT