Lists (1)
Stars
Drive a logged-in ChatGPT Pro browser session over SSH.
Up to 3× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3, Ornith-1.0, ternary Bonsai-27B.
【ICML2026 Spotlight】 T2PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
Breakthrough Method for Agile Ai Driven Development
A Claude Code skill to call Codex, DeepSeek, MiMo, and Grok like a function
Orlando's cloned and refine ai-deadlines from https://aideadlin.es
Source code for WEBSERV: A Browser-Server Environment for Efficient Training of Reinforcement Learning-based Web Agents at Scale
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…
A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases
Hierarchical Reasoning Model Official Release
Entropy Based Sampling and Parallel CoT Decoding
agent q - oss advanced reasoning and learning for autonomous ai agents
Agent S: an open agentic framework that uses computers like a human
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
[ICLR 2025] A trinity of environments, tools, and benchmarks for general virtual agents
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
blueboxd / chromium-legacy
Forked from chromium/chromiumLatest Chromium (≒Chrome Canary/Stable) for Mac OS X 10.7+
The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch…
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.