[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance

A language-model–powered compressor for natural language text

A simple yet powerful agent framework that delivers with open-source models

Self-Adapting Language Models

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"

PromptX · 领先的AI 智能体上下文平台 ｜ PromptX · Leading AI Agent Context Platform

A GeekTime course about constructing a compiler.

MineWorld: A Real-time interactive world model on Minecraft

An open protocol enabling communication and interoperability between opaque agentic applications.

A programming framework for agentic AI

Multi-agent framework, runtime and control plane. Built for speed, privacy, and scale.

A fork of AntennaPod with modern protocols and cipher suites for all Android versions, with no dependencies on Google Services!

A design system for building retro Apple interfaces

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions

A vector search SQLite extension that runs anywhere!

A CodeMirror extension to display inline suggestions

Universal memory layer for AI Agents

Cannoli allows you to build and run no-code LLM scripts using the Obsidian Canvas editor.

Distributed LLM and StableDiffusion inference for mobile, desktop and server.

A UI library to animate and style streaming LLM output

A modern model graph visualizer and debugger

Information about the fractureiser malware (June 2023)

[Fabric Mod] Building Tools and Aesthetic Technology