The agent that grows with you

Xray panel supporting multi-protocol multi-user expire day & traffic & IP limit (Vmess, Vless, Trojan, ShadowSocks, Wireguard, Hysteria, Tunnel, Mixed, HTTP, Tun)

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

The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

Semi-automated research assistant for academic research and software development. Supports Claude Code, OpenCode, and Codex CLI across ideation, coding, experiments, writing, and publication.

Official, Anthropic-managed directory of high quality Claude Code Plugins.

An agentic skills framework & software development methodology that works.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Official code of paper "LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application" (AAAI 2025 Oral)

Minimal reproduction of OneRec

AI agents running research on single-GPU nanochat training automatically

We write sample code for two tower models for retrieval and add RLHF/RLAIF style alignment with a ranking model to make the retrieval more aligned with the ranking model on top

A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more.

An Obsidian plugin that embeds Claude Code as an AI collaborator in your vault

A community collection of OpenClaw use cases for making life easier.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

论文X光机 — Claude Code Skill，解构学术论文，提炼餐巾纸公式

An Open Foundation Model and Benchmark to Accelerate Generative Recommendation

The implementation of the SIGIR 2023 paper "When Search Meets Recommendation: Learning Disentangled Search Representation for Recommendation"

一个可直接落地的端到端推荐系统原型，覆盖离线训练、在线推断与可视化展示，核心链路为：DSSM 双塔召回 → DeepFM 粗排 → 策略补充（热门/冷启动）。

🐹 Deep clean and optimize your Mac.

[KDD'25] LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation.

🔊 让小爱音箱「听见你的声音」，解锁无限可能。

让小爱音箱「听你的」，解锁无限可能。

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

Code for paper "Temporal Interest Network for Click-Through Rate Prediction"

Code for paper "Temporal Interest Network for Click-Through Rate Prediction"