Starred repositories
The end of web parsing. The beginning of scalable pixel-native search.
Perplexity open source garden for inference technology
DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
A simple SWE style browser agent framework that achieves SOTA results on long horizon web tasks.
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
Cuda kernels for leveraging LLM sparsity to improve throughput and decrease the memory requirements during inference and training.
Incremental engine for long horizon agents 🌟 Star if you like it!
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign languag…
TokenSpeed is a speed-of-light LLM inference engine.
Polymarket Data Retriever that fetches, processes, and structures Polymarket data including markets, order events and trades.
1K resolution vision transformers pretrained on 1B human images.
TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.
NVIDIA AITune is an inference toolkit designed for tuning and deploying Deep Learning models with a focus on NVIDIA GPUs.
Dimensional is the agentic operating system for physical space. Vibecode humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seam…
Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
The best-benchmarked open-source AI memory system. And it's free.
Multi-agent systems, memory, planning, reasoning loops
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.
Project N.O.M.A.D, is a self-contained, offline survival computer packed with critical tools, knowledge, and AI to keep you informed and empowered—anytime, anywhere.
Inference repo for Falcon-Perception and Falcon-OCR model, early-fusion, natively multimodal, dense Autoregressive Transformer models.