AI middleware
-
@ai-productivity-tracker/cli
Standalone AI productivity tracking toolkit. One npm package: daemon + stdio MCP + Cursor/Claude hook + browser dashboard.
-
@askjo/camofox-browser
Headless browser automation server and OpenClaw plugin for AI agents - anti-detection, element refs, and session isolation
-
@azure/openai
A companion library to openai for Azure OpenAI.
-
@azure/openai-assistants
An isomorphic client library for Azure OpenAI Assistants.
-
@browserbasehq/stagehand
An AI web browsing framework focused on simplicity and extensibility.
-
@chat-adapter/web
Web adapter for Chat SDK — browser chat UI via the AI SDK useChat stream protocol
-
@hyperbrowser/sdk
Node SDK for Hyperbrowser API
-
@mcp-b/transports
Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs
-
@surething/cockpit
The open-source Claude Code GUI — an IDE-like workbench for parallel AI coding. Drive Claude (default), Codex, DeepSeek, Kimi, or local Ollama in tabs. Terminal, browser & DB bubbles, code review. Self-host on a shared dev box — a seat for every teammate.
-
agent-browser
Browser automation CLI for AI agents
-
agent-browser-workspace
Automate local Chrome browsing with isolated profiles, extract content, save pages to Markdown, and run searches using CLI tools and Node.js APIs.
-
AgentClaw
Build, debug, and deploy declarative agent workflows with this framework for developers and teams.
-
AgentCliBridge
Connect CLI-based AI agents like Claude and Codex to Telegram and Discord with real-time streaming and session management, no SDK needed.
-
agents-cli
The missing toolchain for CLI coding agents. Run any agent on your subscription. Parallel teams, browser driving, Touch ID secrets, routines.
-
agents-control-tower
Monitor and control multiple Cursor agents in one terminal to track status, errors, and progress without switching browser tabs.
-
ai-proofduck-extension
AI writing assistant Chrome extension with Chrome built-in AI (Gemini Nano), local WebGPU/WASM models, and online API support for real-time summarization, proofreading, translation, and text expansion
-
ai-video-search
🧐 Discover key moments in videos with natural language queries using AI, all running locally in your browser for fast and private searches.
-
android-agent
Control Android devices through ADB with this Python automation framework for task execution and phone farm scaling.
-
browser-use-sdk
Official TypeScript SDK for the Browser Use API
-
ccqa
Turn your Claude subscription into a browser test agent
-
claude-code-memory-setup
Reduce token usage and add long-term memory to Claude Code using Obsidian and Graphify for efficient codebase awareness.
-
claude-skill-cinematic-prompt
Generate production-ready cinematic video prompts for Higgsfield AI from reference images and project briefs.
-
cline
Autonomous coding agent CLI - capable of creating/editing files, running commands, using the browser, and more
AI Web -
devflow-ai
🤖 Build and streamline developer workflows with 15 AI-powered, local-first tools designed for open source projects and efficient coding.
-
docs
Dictate text in your browser using this AI-powered voice recognition extension for Chrome.
-
ESP32S3-USB-Keyboard-To-BLE
🔄 Transform any USB keyboard into a Bluetooth device with ESP32-S3, allowing seamless connections to multiple gadgets. Enjoy universal compatibility and low latency.
-
familiar
Keyboard-driven kitty overlays for an AI-agent workflow: a Claude Code session manager, a git reviewer, and a log browser.
-
GemType
Free, open-source Grammarly alternative for Chrome & Safari — AI grammar checker and text rewriter for any website, powered by your own free Google Gemini API key. No account, no tracking, no subscription.
-
GPT-Voyager
Enhance ChatGPT on the web with session management, prompt reuse, formula and Mermaid support, plus export and backup features.
-
h3xassist
🤖 Automate your online meetings with H3xAssist to record, transcribe, and summarize discussions effortlessly. Focus on what matters most.
-
hermes-war-room
Visualize and manage your Hermes agent fleet through a unified browser dashboard for streamlined orchestration and task delegation.
-
Https-Site-Screaper-Social-Commerce-Court-Web
powerful web scraping tool designed to extract data from HTTPS-secured websites, including social media, e-commerce platforms, and court records, for analysis, monitoring, or research purposes.
-
Https-Site-Screaper-Social-Commerce-Court-Web
powerful web scraping tool designed to extract data from HTTPS-secured websites, including social media, e-commerce platforms, and court records, for analysis, monitoring, or research purposes.
-
linkedin-easyapply-antidetection-bot
Automate LinkedIn Easy Apply with stealth browser techniques and AI-driven form filling to test anti-detection and security research methods.
-
MCPSafari
Control Safari on macOS for AI agents with native MCP tools for tabs, forms, HTML, JavaScript, screenshots, and network data
-
metaharness
MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM.
-
multi-publisher
Publish videos to multiple Chinese social media platforms at once with automated browser uploads, saving time and effort for content creators.
-
nano-banana-cli
🖼️ Generate and edit images with ease using the Nanobanana CLI, powered by AI and Google's Gemini models for advanced image manipulation.
-
nano-banana-pro-prompts-recommend-skill
🖼️ Generate stunning images easily with intelligent prompts from a database of 6000+ curated options, tailored to your specific needs.
-
nano-image-generator-skill
🎨 Generate stunning images from text or reference photos with the Nano Image Generator Skill for Gemini 3 Pro, offering versatile outputs and high resolution.
-
NanoBanana-PPT-Skills
🎨 Generate high-quality PPTs with AI, featuring smart transitions and interactive playback for seamless presentations and engaging visuals.
-
nanobrowser
🌐 Automate your web tasks with Nanobrowser, an open-source AI tool that integrates seamlessly into your browser for a smarter browsing experience.
-
NEOTH
Local-first personal AI daemon in Rust — five-tier memory, consent-gated tools, WASM plugin sandbox, multi-provider LLM routing, channels, GUI, signed audit logs, and Babel-Index collapse prediction on its own runtime.
-
notebooklm-toolkit
Manage Google NotebookLM tasks with command-line scripts that replace browser extensions for bulk imports, transcript downloads, and cross-notebook searches.
-
nothumanallowed
Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y
-
Open Hitomi
Floating hedgehog assistant with local chat and browser tools
-
OpenAi-Sora
🎥 Create, edit, and share text or video content effortlessly with SoraFlows, an intuitive browser interface for OpenAI Sora.
-
opencode-browser-automator
Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping
-
Page-agent-UI
Enable natural language commands to automate web tasks directly through a browser sidebar using AI agents for clicks, input, scrolling, and data extraction.
-
periscope-mcp
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.
-
phi
Φ phi — a terminal multiplexer and browser-based control center for AI coding assistants (OpenCode, Claude Code, Antigravity, Pi Coder).
-
pire-browser
Firefox automation CLI and Pi package for AI agents
-
PowerSkills
Enable AI agents to control Windows tasks using PowerShell skills for Outlook, Edge, desktop automation, and structured shell commands in JSON format.
-
prompt-library
📚 Discover and customize prompts for various use cases with our structured library, designed for clarity and ease of use.
-
propagate-id-entra
This example shows how to propagate a user's Entra ID identity end-to-end — from the browser, through an AI Foundry agent with MCP tools, through API Management, all the way to the backend API. No service accounts in the data path.
-
qoder-autopilot
Automate Qoder account registration with integrated captcha solving, anti-detect browser support, and 9Router device token management.
-
reticle
Browser-native, GPU-accelerated editor for very large hierarchical 2D IC-layout scenes, written in Rust (native and WebAssembly).
-
rtl-text-fixer
🌍 Improve Arabic and Persian readability on any website with this Chrome extension that ensures correct text direction automatically.
-
sammapix
Free browser-based image optimization platform — compress, convert WebP, AI rename, HEIC convert, batch resize, 20+ tools. No uploads, 100% private.
-
Scribe
📂 View and annotate STEP files in-browser with precise metadata handling using Flask, CadQuery, and Three.js for CAD documentation.
-
Select2AI_Extension
🖊️ Enhance your browsing experience by selecting text and interacting with GitHub Models AI for instant summaries, explanations, and answers.
-
sequify-server
AI assistant SDK for any website. Users control your app with natural language — no screenshots, no DOM parsing, no guessing. Websites register capabilities, AI calls them directly.为任意网站接入 AI 助手的 SDK。用户用自然语言操控你的应用 — 不截图、不解析 DOM、不靠猜。网站主动注册能力，AI 直接调用。
-
SharkBay
macOS workbench for multi-agent coding — run and monitor multiple AI coding CLIs (Claude Code, Codex, Gemini, Kiro, and more) side by side, with project terminals, an embedded browser, Git at a glance, a Markdown task protocol, and remote control from Telegram.
-
SkyRoads-Codex
Rebuild the original SkyRoads DOS game with a true native port that matches its simulation, rendering, and audio on modern platforms.
-
stably
AI-powered E2E Playwright testing CLI. Stably can understand your codebase, edit/run tests, and handle complex test scenarios for you.
-
superagent
elegant & feature rich browser / node HTTP with a fluent API
-
Task-Management-Dashboard
Manage, track, and organize tasks with a React and TypeScript dashboard featuring real-time search, filters, views, and automatic browser saving.
-
termdeck
Web-based terminal multiplexer with AI agent awareness. Real PTYs, 6 grid layouts, output analyzer, per-terminal theming. tmux in your browser, but it knows what your AI agents are doing.
-
universal-ai-url-prompt
Inject prompts into AI chat web pages via URL parameters for easy sharing and optional automatic submission across major platforms.
-
Unpinched
Detect PinchTab deployments and browser bridge artifacts with a fast, point-in-time scanner for security and forensic analysis.
-
veilbrowser
Stealth browser for AI agents — real Chrome over raw CDP, no Playwright/Puppeteer. TypeScript + MCP-native. Passes sannysoft 57/57, bypasses Cloudflare.
-
voicebridge
Hands-free, two-way voice for your coding agent (Claude Code, Codex, Antigravity, Ollama) from your phone — free for noncommercial use, source-available, no ElevenLabs. Browser Web Speech + a tiny Node bridge over Tailscale HTTPS.
-
vswarm
Multi-tenant T3 Code behind a single URL, gated by Cloudflare Access — each user gets an isolated browser workspace, no pairing, no Tailscale.