Lists (3)
Stars
Minimal kernel to make any AI coding agent stateful. Clone, point your agent, go.
Generate beautiful Manim animations using AI. Describe what you want to animate, and the system generates the code and renders it.
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. The knowledge is av…
Hundreds of models & providers. One command to find what runs on your hardware.
Pulumi - Infrastructure as Code in any programming language 🚀
Production-grade Rust-native trading engine with deterministic event-driven architecture
Shannon Lite is an autonomous, white-box AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities bef…
Agent-RRM: Exploring Reasoning Reward Model for Agents
AirLLM 70B inference with single 4GB GPU
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
An open-source background agents coding system
Lightweight coding agent that runs in your terminal
A production-quality terminal-based profiling tool that diagnoses GPU performance bottlenecks in PyTorch models.
A 3D racing game built with ClojureScript, React and ThreeJS
A self-study for CUDA principles from 0 to 1
A deterministic MLX graph compiler with legality-first operator fusion, cost-model–guided region formation, and a backend for AI-generated kernel synthesis.
Harmful-prompt geometry using the ClearHarm dataset and TransformerLens
A curriculum for learning about gpu performance engineering, from scratch to what the frontier AI labs do
Transformer Architecture from first principles
Transformer-based poker AI agent that learns to play Kuhn Poker through self-play training.
[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.
AutoMQ is a diskless Kafka® on S3. 10x Cost-Effective. No Cross-AZ Traffic Cost. Autoscale in seconds. Single-digit ms latency. Multi-AZ Availability.
High-performance inference engine for large language models optimized for Apple Silicon (MLX backend)
Portfolio Management Workshop by Dan the Quant