Stars
A comprehensive dataset of 433 fitness exercises. Each entry includes name, category, target muscle group, equipment, instructions, thumbnail image, and animation video.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
A Rust toolkit for the Oura Ring (Gen 3/4/5): reverse-engineered BLE protocol, event decoders, and reimplemented data-processing algorithms. Sync, store, and analyze your data locally.
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
A PyTorch native library for training speculative decoding models
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
Ideogram 4: Open image model at the forefront of design
Browser hosting control plane and host runtime for running Chromium sessions
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging
Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x
Fast and memory-efficient classical machine learning operators
ArcticDB is a high performance, serverless DataFrame database built for the Python Data Science ecosystem.
MathCode: A Frontier Mathematical Coding Agent
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
Deploy headless browsers in Docker. Run on our cloud or bring your own. Free for non-commercial uses.
A multi-hypervisor VM runtime for OCI images, supporting Cloud Hypervisor, Firecracker, QEMU, and Apple Virtualization.framework.
Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop and mobile.
A simple, fast and robust program-aware agentic inference system.
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
Block-R1: Multi-domain dLLM RL Post-training Benchmark.