This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

Fine-tuning base models to build robust task-specific models

Understanding R1-Zero-Like Training: A Critical Perspective

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

[ICLR 2025 Oral] PyTorch code for the paper "Open-World Reinforcement Learning over Long Short-Term Imagination"

Verifiers for LLM Reinforcement Learning

Towards Human-Sounding Speech

A Conversational Speech Generation Model

No fortress, purely open ground. OpenManus is Coming.

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断

multiple SillyTavern server tools | 多实例SillyTavern云酒馆管理工具

LLM Frontend for Power Users.

Effective Python: Third Edition — Source Code and Errata for the Book

The ultimate LLM/AI application development framework in Golang.

【deepin源移植】Debian/Ubuntu上的QQ/微信快速安装方式

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs

Autonomous agents for everyone

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭…

AI companions with memory: a lightweight stack to create and host your own AI companions

Paper list for Personal LLM Agents

An attempt to build a working, locally-running cheap version of Generative Agents: Interactive Simulacra of Human Behavior

Remote Procedure Call

Build resilient language agents as graphs.