Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, continuous awareness.
#agents
630 posts
🌋 Build AI agents that seamlessly combine LLM reasoning with real-world actions via MCP tools — in just a few lines of TypeScript.
Build effective agents using Model Context Protocol and simple workflow patterns
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
Demo for Anonymous Credentials Token for Rate-Limiting Agents
An AI agent skill that provides expert guidance on ParadeDB
Human Interaction MCP Tool
A minimal AI Agent runtime demonstrating tool calling, agent loops, context management, and extensible architecture.
Persistent memory and identity for AI agents. Free hosted API.
Rust reference SDK for ARCP (Agent Runtime Control Protocol).
Run AI agents inside sandboxes over WebSockets - from the engineering team at https://getlark.ai
Markdown-native websites. HTML for humans, Markdown for agents. Zero build.