Starred repositories
Fastest LLM inference runtime for Apple Silicon
Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.
My learning notes for ML SYS.
The best-benchmarked open-source AI memory system. And it's free.
Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.
OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Archived — ML Intern is no longer maintained. Continue with HuggingChat.
Awesome-LLM4Kernel: A curated list of papers with codes related to LLM-based kernel generation and optimization.
An awesome list of Agent Harness engineering resources, including GitHub projects, tools, benchmarks, and practical guides.
A community collection of OpenClaw use cases for making life easier.
Dr.Jit — A Just-In-Time-Compiler for Differentiable Rendering (core library)
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Diagram as Code Tool Written in Rust with Draggable Editing
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
The automatic work journal/time tracker. Privately turns your screen into a timeline of what you actually accomplished. Open-source and local-first.
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…
A curated list of materials on AI efficiency
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
A configuration framework that enhances Claude Code with specialized commands, cognitive personas, and development methodologies.
Complete solutions to the Programming Massively Parallel Processors Edition 4
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Low-latency NUMA-aware fork-join thread-pool with zero allocations, syscalls, CAS, or false-sharing on the hot path for C++, C, Rust, Zig & Mojo 🍴
KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale
Open-source implementation of AlphaEvolve
🔥Highlighting the top ML papers every week.