|
Agent Web Interface — MCP Browser Automation for AI Agents
Compact semantic snapshots. Stable element IDs. No raw DOM noise. The MCP server that gives AI agents a precise, token-efficient browser interface.
|
81 % |
|
Reflow — Your agents test your code, not your product
Give your coding agent the product context and runtime evidence a code diff misses. Run real journeys, compare snapshots and review what changed before you m...
|
79 % |
|
HighX — the reactive application runtime for Cloudflare
HighX is a TypeScript framework for Cloudflare. Write plain typed functions — HighX keeps your screens live, your pages hydrated, and your AI agents on a leash.
|
79 % |
|
Pulse — The spec-first web framework for AI agents
One plain JavaScript object per page. Zero runtime dependencies. Server data, state, mutations, view. Built for AI agents to write production web apps.
|
79 % |
|
htmlbin — agent-first HTML hosting
Your agent writes HTML. You get a URL. One human click to start, then your agent publishes on its own.
|
79 % |
|
buttercup.sh — a friendly place to build AI agents in your browser
Learn to build AI agents in a friendly browser workshop where you can write, run, inspect, and undo every step.
|
79 % |
|
WebPilot.si: a browser that remembers, for your AI agents
WebPilot.si gives your AI agent its own real Chromium that stays logged in between runs. Agents connect over MCP, programs over REST, and you can watch or ta...
|
79 % |
|
Tilda for Mac: a JavaScript runtime for your coding agent
Most browser tools make your agent stop after every click, read the page, and ask the model what to do next. With Tilda, Claude Code, OpenCode, and Grok hand...
|
78 % |
|
Cloud Browser Infrastructure for AI Agents | Tabfleet
Launch and control isolated cloud browsers for AI agents through MCP, REST APIs, the TypeScript SDK, or CLI, with live viewing and embedding.
|
78 % |
|
Pluckor — give an AI agent a real browser
Pluckor gives an AI agent a real Chrome to drive — navigate, read rendered HTML, run JS, click, type, scroll. Extract from sites that block headless and Play...
|
78 % |
|
Golem: the durable runtime for AI agents
Golem runs AI agents, their tools and their artifacts. Each agent runs in a lightweight WebAssembly VM that resumes mid-function after node restarts, rescali...
|
78 % |
|
agnt.fyi — Browser API for agents
|
78 % |
|
Riddle - Hosted Execution for AI Agents
Hosted execution infrastructure for AI agents: browsers, server previews, screenshots, console logs, network HAR, and proof receipts.
|
78 % |
|
Browserable
Open source JS browser automation library for AI agents
|
78 % |
|
Kortyx | Write the agent logic. The runtime is already built.
Kortyx is a TypeScript framework for agent workflows, streamed React state, human interrupts, persisted runs, session branching, and tracing.
|
78 % |
|
agents.cli
A publication on context engineering, closing the gap between AI coding agents and the context they don't have.
|
78 % |
|
Cogitator - AI agents that survive production
Self-hosted, production-grade AI agent runtime for TypeScript: multi-provider LLMs, tools with approvals, memory and RAG, DAG workflows, multi-agent swarms,...
|
78 % |
|
Scout — Browser Automation Environment for AI Agents
Scout is a browser automation environment for AI agents. Observe, understand, and operate real browsers, with a runtime that spans automation, canvas, extens...
|
78 % |
|
ACT — Agent Content Tree | ACT
An open standard for publishing AI-readable, structured content from any website, CMS, or app.
|
78 % |
|
Bounded Systems — a checkpoint in front of your coding agent
Your coding agent runs with your access. Bounded Systems puts one checkpoint in front of every privileged action: it checks who is asking and what they're al...
|
78 % |
Detected social media networks