Stars
AI agents running research on single-GPU nanochat training automatically
微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎,预测万物
IronClaw is OpenClaw inspired implementation in Rust focused on privacy and security
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
Muon is an optimizer for hidden layers in neural networks
Use Muon optimizer instead of AdamW.
PyTorch implementation of the Mamba-3 architecture
Understand and test language model architectures on synthetic tasks.
RynnBrain: Open Embodied Foundation Models
Pytorch library for fast transformer implementations
[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
Unified framework for robot learning built on NVIDIA Isaac Sim
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSim), and more.
[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
Causal depthwise conv1d in CUDA, with a PyTorch interface
"AI-Trader: Can AI Beat the Market?" Live Trading Bench: https://ai4trade.ai Tech Report Link: https://arxiv.org/abs/2512.10971
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Algorithm powering the For You feed on X
Source code for the X Recommendation Algorithm
LLM驱动的 A/H/美股智能分析器:多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送,零成本定时运行,纯白嫖. LLM-powered stock analysis system for A/H/US markets.
AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …