Designing, evaluating, and shipping autonomous AI agents.
7657 posts
让任意 AI 客户端自动调试微信小程序/小游戏：截图、模拟触控、读日志、一键重开；配合 wechat-dev-skill 自动巡检四来源报错。
A cognitive substrate for AI agents — hyperdimensional memory with first-class goals, beliefs, sensory, self-model, and a non-destructive un...
Self-hosted multi-agent AI platform, orchestrate specialized agents across Telegram, WhatsApp, and web with 90+ tools, 15 autonomous scraper...
Multi-vendor AI coding knowledge base. Auto-synced docs for Claude Code, Cursor, Codex, OpenAI, Gemini. Long-term context for AI agents — cl...
Single-tool MCPorter bridge extension for pi and Model Context Protocol (MCP) servers.
Wave-based development lifecycle and code intelligence framework for AI-assisted engineering. Includes semantic + graph indexing, MCP tool s...
Kanban board for AI agent pipelines
An AI-driven dynamic protocol fuzzer for the Model Context Protocol (MCP). Prove runtime exploitability by discovering state violations, tra...
Specialized agents, MCP servers, skills, and a visual dashboard for Claude Code. MIT.
MCP server for Hey.com: read, send, search, and organise email from Claude or any MCP client. Runs locally, stores no credentials, respects...
Build Your Own Agentic AI with SoloEngine. Achieve Loop Engineering — by simply dragging and dropping.
Rust multi-agent LLM framework — OpenClaw alternative. WhatsApp + Telegram + Gmail + browser agents on a single binary. NATS broker, MCP cli...
