Starred repositories
Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news aggregation, entity profiles, conflict detection, document analysis. No API keys…
A simple Markdown viewer for reading .md files
A Minimalist, Batteries-included Repository for Advancing World Model Science.
A backup-first Codex skill for keeping local Codex state fast, clean, and recoverable.
A liquid glass effect library for the web. Apply realistic glass refraction, blur, chromatic aberration, and lighting effects to any HTML element using WebGL shaders.
High-performance uncensored Gemma-4-26B inference on NVIDIA DGX Spark using vLLM - 45+ tok/s
To provide AI with Mermaid chart rendering capability, supporting both SVG and ASCII output formats
Lightweight nVidia telemetry and terminal system monitor - built for any architecture - Jetson, GB10, GB200, H100
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
🔥 LeetCode for PyTorch — practice implementing softmax, attention, GPT-2 and more from scratch with instant auto-grading. Jupyter-based, self-hosted or try online.
BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model | NeurIPS '25
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Native Mermaid and SVG visual skill for Codex-compatible clients.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
🏠 Ask Claude about Korean apartment prices — powered by 국토교통부 open API
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
PaperBanana: Automating Academic Illustration For AI Scientists
An app to monitor the (Codex) situation
Show usage stats for OpenAI Codex and Claude Code, without having to login.
Docker configuration for running VLLM on dual DGX Sparks