Stars
open-arms-mini: cheap human like teleoperation device that supports human in the loop corrections
TRACER: replace 90%+ of your LLM classification calls with a traditional ML model. Formal parity guarantees. Self-improving.
Lightweight LLM firewall: masks PII, routes calls, leaves zero trace.
Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds. 面向游戏与虚拟世界的AI原生渲染引擎
국가법령정보MCP | 법제처 39개 API → 14개 MCP 도구. 법령·판례·조례·조약을 AI로 검색·조회·분석 | 39 Korean legal APIs → 14 MCP tools
REAP: Router-weighted Expert Activation Pruning for SMoE compression
Implementation of Fast Weight Attention
Official implementation for Training LLMs with MXFP4
Implements harmful/harmless refusal removal using pure HF Transformers
tokenbender / parameter-golf
Forked from openai/parameter-golfTrain the smallest LM you can that fits in 16MB. Best model wins!
Comparative study and experimentation on standard vs mHC vs attention residual (full and block)
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
Original reference implementation of the CUDA rasterizer from the paper "StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering"
An unofficial implementation of absGS
Open-source framework for turning expert knowledge into PII-free synthetic conversational data and production-ready LoRA adapters.
An agent for CUDA compute-communication kernel co-design
A lightweight inference engine supporting speculative speculative decoding (SSD).
Open-source CUDA compiler targeting multiple GPU architectures. Compiles .cu to AMD and Tenstorrent GPU's
Voice-to-text app for macOS to transcribe what you say to text almost instantly
Agent harness to publish your history from Claude Code et al. as Huggingface datasets.
A collection of research papers on low-precision training methods
The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".
Shared Middle-Layer for Triton Compilation