精选仓库

qiaomu-goal-meta-skill

Turns vague work into a copy-ready Codex `/goal` command with defaults, verification, boundaries, and pause conditions.

claude-design-mcp

A local MCP design studio that lets Claude Code generate, iterate, and screenshot HTML designs from the CLI using only your existing Claude subscription, with full auditability and no reverse engineering.

kill-ai-slop

An interactive field guide and agent skill that catalogs and fixes the stereotypical visual patterns of AI-generated web design through before-after demos and automated scanning.

recensa

A self-hosted viewer for Claude Code session transcripts that indexes and renders every session as a readable, searchable, and auditable conversation with full-text search, diff views, and multi-agent support — all running locally on your machine with no data uploads.

hermes-agent

A self-improving AI agent with a built-in learning loop that autonomously creates, refines, and persists skills from experience while operating across multiple platforms and deployment environments.

openclaw

A local-first personal AI assistant that operates across 20+ messaging platforms with voice, canvas, and multi-agent routing capabilities.

learn-agent

A step-by-step, zero-dependency tutorial series that distills production-proven engineering patterns from a real open-source desktop coding agent into runnable single-file code.

CSswitch

Use any third-party OpenAI-compatible API to run Claude Science's AI agent research platform without a Claude subscription.

hermex

A native SwiftUI iPhone app that lets you control your self-hosted AI agent directly from your phone, keeping data and compute entirely on your own hardware.

Fundamental-Ava

A scalable many-agent simulation framework that detects emergent civilization-level properties through tiered memory, bounded concurrency, and statistical analysis.

LongCat-2.0

LongCat-2.0 is a 1.6-trillion-parameter MoE model pretrained on over 35 trillion tokens using domestic AI ASIC superpods, achieving 1M-token context and strong performance on coding, agentic, and reasoning benchmarks.