Stars
Temporalmesh-transformer. It is the first architecture to simultaneously fuse dynamic graph topology, token-level adaptive compute, and temporal semantic decay into a single unified model. No prior…
DKMS package for MediaTek MT7927/MT6639 Filogic 380 WiFi 7 + Bluetooth on Linux
Drop-in AGENTS.md that makes every coding agent behave like a senior engineer instead of an eager intern. Kills sycophancy, stops drive-by refactors, forces verification loops. Synthesizes Karpathy…
DeepTutor: Agent-native Personalized Tutoring. https://deeptutor.info/.
RULEC-GEC is a dataset of sentences written by learners of Russian and annotated for mistakes.
Открытые лингвистические датасеты: тональный словарь русского языка КартаСловСент, датасет по семантике, ассоциативный граф и датасет по орфографическим ошибкам и опечаткам.
An agentic skills framework & software development methodology that works.
Using BFS & DFS like techniques over LLMs for iteratively exploring the solution search space at scale.
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
Data and Code for ACL 2021 Paper "Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning"
Game sound effects for Claude Code — Warcraft Peon voice lines while you code! Work work! 🔨
Vane is an AI-powered answering engine.
A Recipe for Building LLM Reasoners to Solve Complex Instructions
A community collection of OpenClaw use cases for making life easier.
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
A Model Context Protocol server for searching and analyzing arXiv papers
CIFAR-10 speedrun: Trains to 94% accuracy in 1.98 seconds on a single NVIDIA A100 GPU.
Muon is an optimizer for hidden layers in neural networks
Accelerating MoE with IO and Tile-aware Optimizations
💫 Toolkit to help you get started with Spec-Driven Development