Highlights
- Pro
Lists (1)
Starred repositories
DeepSeek Harness: Everything is a Plugin.
Implement a reasoning LLM in PyTorch from scratch, step by step
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for p…
LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…
Pretty fancy and modern terminal file manager
Difference-in-Differences causal inference in Python. Callaway-Sant'Anna, Synthetic DiD, Honest DiD, event studies. sklearn-like API, validated against R.
Build local voice agents with open-source models
IHBench: evaluation toolkit for post-interruption recovery in voice agents
Companion code for the global workspace interpretability paper
Submodular benchmark selection: code and assembled score matrices from the paper (Smola, 2026).
Textbook on reinforcement learning from human feedback
Prompt Injection as Role Confusion
Flexible Statistical Modeling with Bayesian Additive Regression Trees
A skill for writing technical documentation for human readers, iteratively, with author reviews at each step.
Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.
Are people writing more papers in the age of AI? Working-paper & journal-submission growth across arXiv, NBER, SSRN, and AEA journals.
An agentic skills framework & software development methodology that works.
[CVPR 2026] Official Implementation of Dynamic erf (Derf).
Minimal plugin that lets Claude Code call you on the phone.
Control your claude code from your apple watch
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Fine-tuning Vietnamese Text-to-speech model (VITS)
Fast and local neural text-to-speech engine