Automate your mobile devices with natural language commands - an LLM agnostic mobile Agent 🤖

[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

Official inference repo for FLUX.2 models

"AI-Trader: Can AI Beat the Market?"

ValueCell is a community-driven, multi-agent platform for financial applications.

An open-sourced implementation for "Agentic Context Engineering (ACE)" methon from *Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models* (arXiv:2510.04618).

Repository for Multi-Camera rPPG dataset utilities and rPPG in general

A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Text-audio foundation model from Boson AI

Implementation and explorations into Blackbox Gradient Sensing (BGS), an evolutionary strategies approach proposed in a Google Deepmind paper for Table Tennis

[ICLR2024] TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning

Official implementation of the paper "Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer". https://kiedani.github.io/CVPRW…

Local Video-LLM powered AI Baby Monitor

Memory for AI Agents; SOTA in AI Agent Memory; Announcing OpenMemory MCP - local and secure memory management.

Toolkit for linearizing PDFs for LLM datasets/training

An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs

Code for LATTE-MV: Learning to Anticipate Table Tennis hits from Monocular Videos

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Get your documents ready for gen AI

A powerful tool for creating fine-tuning datasets for LLM

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

From Hours to Minutes: Lossless Acceleration of Ultra Long Sequence Generation

Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs

Repository containing code and notebooks exploring how to build reinforcement learning agents that play tennis in MujoCo

A fast communication-overlapping library for tensor/expert parallelism on GPUs.