ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Codex 降智测试

Continue-thinking middleware for Codex / OpenAI Responses-compatible APIs.

Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic

花叔的内容创作 Skills 合集 - AI审校、选题生成、视频大纲、素材搜索等 11 个实用技能

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

🚀 Open source Claude Code CLI source code. Advanced AI Agent for developers. Includes TypeScript codebase for LLM tool-calling, agentic workflows, and terminal UI. Remember this is just the skeleto…

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

RevealLayer: Image Decomposition via Disentangling Hidden and Visible Layers, ICML2026

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Nano vLLM

[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.

Typed atomic notes in a graph — a Zettelkasten that scales. Knowledge construction with Building Blocks, Folgezettel trails, and the Dialectic Knowledge System (DKS).

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Democratizing Reinforcement Learning for LLMs

⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)

AcadHomepage: A Modern and Responsive Academic Personal Homepage

The code and data of We-Math 2.0.

Python client for the Polymarket CLOB

Official Implementation of OmniAlpha.

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Starter kit for creating custom pools and hooks contracts on Balancer v3

Qwen-Image text to image lora trainer

[NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains