High-speed Large Language Model Serving for Local Deployment

26m function call model that runs on incredibly small devices

Examples, end-2-end tutorials and apps built using Liquid AI Foundational Models (LFM) and the LEAP SDK

LLM-based QAG framework for MT Evaluation

LLM-based Literary Translation evaluation metric with Professional Question Answering

Visualization playground for sparse autoencoders using BERT & GloVe

Gazeta: Dataset for automatic summarization of Russian news / Газета: набор данных для автоматического реферирования на русском языке

Autonomous game development for Godot and Bevy with Claude Code and Codex

Glamourous agentic coding for all 💘

Toolkit for Prompt Compression

Prompt compression and optimization

Ouroboros — self-creating AI agent. Born Feb 16, 2026.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Source Code of Arena Leaderboard Methodology

Arena-Hard-Auto: An automatic LLM benchmark.

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

Bridge Neovim and OpenCode AI to stay in your flow.

Fully automatic censorship removal for language models

Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community

Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀

Companion code to https://arxiv.org/abs/2402.15491

the official code for "ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases"

Code release for "TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices"