Starred repositories
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Obsidian + Claude Code: Rebuild Your Second Brain with AI · 橙皮书系列 · 用AI重建你的第二大脑
智能闲鱼客服机器人系统：专为闲鱼平台打造的AI值守解决方案，实现闲鱼平台7×24小时自动化值守，支持多专家协同决策、智能议价和上下文感知对话。
开源运维平台：面向中小型企业设计的轻量级无Agent的自动化运维平台，整合了主机管理、主机批量执行、主机在线终端、文件在线上传下载、应用发布部署、在线任务计划、配置中心、监控、报警等一系列功能。
Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。
The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"
An open-source, AI-integrated, cross-platform terminal for seamless workflows
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
AIGCPanel 是一个简单易用的一站式AI数字人系统，支持视频合成、声音合成、声音克隆，简化本地模型管理、一键导入和使用AI模型。
An effort to track benchmarking results over widely-used datasets for ASR.
adefossez / demucs
Forked from facebookresearch/demucsCode for the paper Hybrid Spectrogram and Waveform Source Separation
Code for the paper Hybrid Spectrogram and Waveform Source Separation
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
Examples for Recommenders - easy to train and deploy on accelerated infrastructure.
A unified architecture deep learning framework designed specifically for ultra-large-scale sparse models.
Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels
CosyVoice_DPO_NOTES: Supercharge Your Cosyvoice model with Cutting-Edge DPO Fine-Tuning!
KDD19 Tutorial: From Shallow to Deep Language Representations: Pre-training, Fine-tuning, and Beyond
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
Forked vLLM that supports higgs-audio model
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…