llm-internals
Learn LLM internals step by step - from tokenization to attention to inference optimization.
HYSEN LABS DIRECTORY
Capability tag · curated repositories and deep analysis.
Learn LLM internals step by step - from tokenization to attention to inference optimization.
Build Anything with AI Agents
Open-source Agent Skill that drives the BaoCut macOS app CLI (transcribe · subtitle · translate · cut) from Claude Code, Codex, and other agents
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
Local first semantic and hybrid BM25 grep / search tool for use by AI and humans!
"Small vector" optimization for Rust: store up to a small number of items on the stack
AIdea is an all-in-one app supporting GPT and domestic Chinese LLMs like Tongyi Qianwen and Wenxin Yiyan, plus Stable Diffusion text-to-image, image-to-image, SDXL 1.0, super-resolution and image colorization.
Whatomate is an open-source WhatsApp integration
Native macOS App Store Connect tool with MCP. Submit iOS apps to App Store with AI agents
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Docs for humans and agents, built on Astro
Generate your Twitter bio with AI
Synthetic data curation for post-training and structured data extraction
2026年科学上网最稳翻墙软件,几款中国好用的VPN推荐
Router that virtually distributes inference across connected devices in the home.
Inference Microsoft Florence2 VLM
基于 REA 深度拆解并高保真还原 Claude 官方桌面端 UI。还原 30 个独立 React 组件与 8 项硬核交互物理算法,附带 3000+ 行逆向分析手册。
An agent skill that mirrors a website, rebuilds it from the minified code line by line, and verifies the result with automated diffs.
Buttercup finds and patches software vulnerabilities
Lightweight coding agent written in Rust, optimized for memory footprint and performance