d-wwei/labloop
Autonomous experiment loop skill for Claude Code. Give it a codebase and a metric — it experiments forever. Generalized from Karpathy's autoresearch.
Autonomous experiment loop skill for Claude Code. Give it a codebase and a metric — it experiments forever. Generalized from Karpathy's autoresearch.
npx skills add d-wwei/labloopAutonomous experiment loop skill for Claude Code. Give it a codebase and a metric — it experiments forever. Generalized from Karpathy's autoresearch.
Auto-generate a structured project knowledge base (CONTEXT.md) from codebase analysis. Inspired by mattpocock's shared language (52K stars) and jcode's semantic memory.
Skill + Agent + Model + Thinking depth — auto-routed before any tool fires. One SKILL.md for Claude Code. 90% routing accuracy, per-step model enforcement, 30%+ savings on multi-step chains.
Persistent local memory layer for AI. Glia uses a Chrome extension and a native MCP server to sync context and decisions from your browser chats (Claude, ChatGPT, DeepSeek) straight to your local IDE agents (Cursor, Claude Code, Windsurf) powered by a local SQLite knowledge graph.
Advanced tabular parsing routines bundled into semantic agents tasked with reading complicated corporate PDF reports.
Agent skill repository discovered by 10x-chat research.
AI agent platform for frontend engineering with RAG, Skills, SDD, MCP and so on | 通过多种适配前端工程的技术进行赋能的智能体，支持：CLI、VSCode插件、LoRA模型、MCP服务