Frontier Models playing the board game Diplomacy.

Diplomacy: DATC-Compliant Game Engine with Web Interface

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

A vector index built on TurboQuant, written in Rust with Python bindings

Effortlessly compose, extend, and observe every service in real-time for the first time ever.

A lightweight keyboard for Android

Learn it. Build it. Ship it for others.

Adala: Autonomous DAta (Labeling) Agent framework

🙌 OpenHands: AI-Driven Development

The headless browser for AI agents and web scraping

A simple multiuser multiboard task MCP server managed via kanban board interface. Created to allow simple self hosted agent task management.

LLM inference in C/C++

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

PersonaPlex code.

Claude Code without any telemetry - the perfect cli to combo with CCR

Curated list of the best truly open-source AI projects, models, tools, and infrastructure.

Experimental platform for studying emergent behavior in large-scale multi-agent reinforcement learning environments with evolutionary dynamics, PPO training.

A unified interface for AI in your terminal.

AI agents running research on single-GPU nanochat training automatically

EB1A Green Card Template for Self-Petition

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

This SDK generates datasets for training Video LLMs from youtube videos.

Lean 4 programming language and theorem prover

LLM101n: Let's build a Storyteller

Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment

Columnar database on SSD NVMe

The fastest ACID-transactional persisted Key-Value store designed as modified LSM-Tree for NVMe block-devices with GPU-acceleration and SPDK to bypass the Linux kernel

This is the source code for our (Tobias Ziegler, Carsten Binnig and Viktor Leis) published paper at SIGMOD’22: ScaleStore: A Fast and Cost-Efficient Storage Engine using DRAM, NVMe, and RDMA.

[ARCHIVED] See your robot moving autonomously in simulation - today! 🚀