中国专利.skill：从项目文档到交底书编写（挖点·查新·脱敏成文）+ 专利通俗解读（叙事·图谱·Obsidian 私库）。

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Expert code review skill: SOLID, security, performance, error handling, boundary conditions

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

An agentic skills framework & software development methodology that works.

Official implementation of Controlled Self-Evolution for Algorithmic Code Optimization

AI agent for Home Assistant — talk to your home, create automations in plain language, analyze cameras with face recognition, and get proactive anomaly alerts. Cloud LLMs or fully local via Ollama.

MCP server that gives AI assistants control over your Home Assistant. Including 50+ tools over 3 transports. Batteries included 🔋

A MCP server for Home Assistant

基于HomeAssistant对外开放API，基于Qwen大模型的简易UI Demo

Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude mod…

Xiaomi Miloco

Post-training with Tinker

The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"

The official repository of paper "Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models''

Text-audio foundation model from Boson AI

神级Cursor Rule

An open-source AI agent that brings the power of Gemini directly into your terminal.

This package is a collection of datasets for evaluating AI Models in the context of Home Assistant.

This project aims to seamlessly connect the Zhipu Qingyan language model with the Home Assistant (HASS) platform to provide more intelligent home automation management.

🏡 Open source home automation that puts local control and privacy first.

A Home Assistant integration & Model to control your smart home using a Local LLM

Democratizing Reinforcement Learning for LLMs

Extractive text summarization using seq2seq, PGN and coverage machanism.

A series of large language models trained from scratch by developers @01-ai

Math-OCR-Zero: A high-quality mathematical dataset for reinforcement learning in multimodal large models

复现大模型相关算法及一些学习记录

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

Toolkit for linearizing PDFs for LLM datasets/training