MiroMind Research Agent: Fully Open-Source Deep Research Agent with Reproducible State-of-the-Art Performance on FutureX, GAIA, HLE, BrowserComp and xBench.

SkyRL: A Modular Full-stack RL Library for LLMs

MiroTrain is an efficient and algorithm-first framework for post-training large agentic models.

A PyTorch native platform for training generative AI models

Bootstrap Kubernetes the hard way. No scripts.

how to optimize some algorithm in cuda.

🔥[NeurIPS'25] DeepFund: Pilot for Your Next Fund Investment

A JAX-native LLM Post-Training Library

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

SPEC-RL: Accelerating On-Policy Reinforcement Learning via Speculative Rollouts

✨ 一站式 LLM 聊天机器人平台及开发框架 ✨ 支持 QQ、QQ频道、Telegram、企微、飞书、钉钉 | 知识库、MCP 服务器、OpenAI、DeepSeek、Gemini、硅基流动、月之暗面、Ollama、OneAPI、Dify

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

JAX backend for SGL

[Support 0.49.x]（Reset Cursor AI MachineID & Bypass Higher Token Limit） Cursor Ai ，自动重置机器ID ， 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machi…

Display and control your Android device

Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

Use Claude Code with your Copilot subscription

DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit

DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

iFlow cli is a comprehensive command-line intelligence that embeds in your terminal, analyzes your repositories, does coding tasks, interprets your needs across contexts, and boosts efficiency by p…

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Efficient Compute-Communication Overlap for Distributed LLM Inference

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, c…

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

The official repository of the dots.vlm1 instruct models proposed by rednote-hilab.