The agent engineering platform. Available in TypeScript!

你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

An AI Hedge Fund Team

Meridian is an MMM framework that enables advertisers to set up and run their own in-house models.

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.

Specification and documentation for Agent Skills

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

GLM-5: From Vibe Coding to Agentic Engineering

Latitude is the open-source prompt engineering platform to build, evaluate, and refine your prompts with AI

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

Agent S: an open agentic framework that uses computers like a human

The open source coding agent.

摸鱼岛🎣后端 基于爬虫 ➕ Netty ➕ SpringBoot ➕Redis➕ MySQL 开源🌟一站式摸鱼网

🦄🦄🦄AI赋能股票分析：AI加持的股票分析/选股工具。股票行情获取，AI热点资讯分析，AI资金/财务分析，涨跌报警推送。支持A股，港股，美股。支持市场整体/个股情绪分析，AI辅助选股等。数据全部保留在本地。支持DeepSeek，OpenAI， Ollama，LMStudio，AnythingLLM，硅基流动，火山方舟，阿里云百炼等平台或模型。

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

No fortress, purely open ground. OpenManus is Coming.

摸鱼岛🎣前端基于 React + Antd 开发的开源🌟摸鱼网

2025精选：算法题库合集，涵盖大厂面试、校招笔试及LeetCode等热门平台经典题目，助你轻松拿下offer！

Minimal reproduction of OneRec

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

一键监控今日头条、百度热搜、微博、抖音、知乎、B站等35个平台，智能关键词筛选，自动生成热点分析报告。支持企业微信、飞书、钉钉、Telegram推送，30秒网页部署，1分钟手机通知，无需编程基础。还有文字和图片版api可调用

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Conformal Interval Estimation in Regularized Insurance Models

Classic papers and resources on recommendation

Train transformer language models with reinforcement learning.

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

Industry leading face manipulation platform

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)