Alireza29675/desk
🚧 WIP experiment — a local-first visual communication channel between AI agents and a human operator. MCP server + live viewer (typed artifacts, semantic-anchored comments, realtime). Built with Claude Code.
🚧 WIP experiment — a local-first visual communication channel between AI agents and a human operator. MCP server + live viewer (typed artifacts, semantic-anchored comments, realtime). Built with Claude Code.
npx add-skill Alireza29675/desk🚧 WIP experiment — a local-first visual communication channel between AI agents and a human operator. MCP server + live viewer (typed artifacts, semantic-anchored comments, realtime). Built with Claude Code.
AI-guided self-hosting for 950+ open-source apps on any cloud. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes — catalog self-improves from user feedback.
Claude Code skill: audit or build landing pages against 11 patterns from Stripe, Airbnb, Coinbase, DoorDash, Dropbox, GitLab, Instacart, Gusto
A high-performance research orchestrator in Go & React. Deploys parallel 'Legs' to crawl the web, scales insights with a provider-agnostic AI router (GPT, Gemini, DeepSeek, Ollama, Claude), and visualizes intelligence on a dynamic, interactive Detective Board.
🤖 Build efficient multi-agent workflows with the OpenAI Agents SDK, supporting OpenAI APIs and 100+ other LLMs for flexible solutions.
Explore Claude Code's Agent Harness architecture with a clear breakdown of its runtime, tools, and control flow for AI agent builders
Structured study guide for Claude Code, covering slash commands, CLAUDE.md, spec-driven development, plan mode, custom commands, skills, sub-agents, and MCP.