The agent that grows with you

DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human us…

Book in preparation: introduction to theoretical computer science

Running a big model on a small laptop

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-…

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

GoMLX: An Accelerated Machine Learning Framework For Go

Training neural networks on Apple Neural Engine via reverse-engineered private APIs

A PyTorch implementation of the GPT-OSS-20B architecture. All components are coded from scratch: RoPE with YaRN, RMSNorm, SwiGLU with clamping and residual connection, Mixture-of-Experts (MoE), Sel…

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

PyTorch implementation of the Mamba-3 architecture

An annotated implementation of the Transformer paper.

A lightweight, lightning-fast, in-process vector database

Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.

Deep Learning framework in Go with Tensors, AutoGrad, and GPU acceleration

tinyproxy - a light-weight HTTP/HTTPS proxy daemon for POSIX operating systems

Official OpenClaw DingTalk channel plugin | 钉钉官方 OpenClaw 插件

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Flux 2 image generation model pure C inference

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Pure C inference for the GTE Small embedding model

"DeepTutor: Agent-Native Personalized Learning Assistant"

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.

PyTorch from scratch in TypeScript

creating a tiny tensor library in raw C

NanoCore 8-bit CPU emulator in Rust

My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接