Russian speech technology links

MCP server for Moltbook — the social network for AI agents

Lets your agent loose block game

Вопросы с собеседований на позицию Machine Learning Engineer

Russian fine tune of sopranoTTS

Войс чат на русском языке

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Community maintained hardware plugin for vLLM on Apple Silicon

Paper List of Minecraft Agents

A lightweight Python package for Automatic Speech Recognition using ONNX models

A list of free LLM inference resources accessible via API.

🧙 Advanced Minecraft Bot Tool. Deploy automated bots for server testing, automation, and development.

Official Implementation for Optimus-3: Dual-Router Aligned Mixture-of-Experts Agent with Dual-Granularity Reasoning-Aware Policy Optimization

Minecraft mod that allows you to record and replay player movements

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

[ICLR 2026] Efficient Agent Training for Computer Use

Mobile-Agent: The Powerful GUI Agent Family

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

Dream Recorder is an open-source venture by Modem. Developed in close collaboration with Mark Hinch (software & hardware), Ben Levinas and Joe Tsao (industrial design), and Alexis Jamet (illustrati…

Multi-layer text moderation system

100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

Framework for testing vulnerabilities of large language models (LLM).

Official repository for LTX-Video

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

Unofficial stable and pre-release builds of the Zed editor for Windows, with version and release type matching. Easy install via scoop or pwsh script. Not affiliated with Zed Industries.