InftyAI is a non-profit organization focused on building AI infrastructure, including model training & inference, agentic systems and more. We 💙 Open Source.

• Awesome-Kernel-Agents: A curated list of AI agents for GPU kernel generation, optimization, and verification.
• Awesome-LLMOps: A curated list of the best LLMOps tools.

• AMRS: The adaptive model routing system for exploration and exploitation.
• llmaz: Easy, advanced inference platform for large language models on Kubernetes.
• mlx: Rust bindings for Apple's MLX framework.
• PUMA: A lightweight, high-performance model engine for local AI.

• Nebula: The control plane for GPUaaS — across neoclouds, hyperscalers, and your own infrastructure.

• alphatrion: The open-source recursive self-improvement system.
• SandD: A lightweight sandbox daemon for secure agent execution in isolated environments.

• omnistore: A unified Python client for various object-store providers.

• Manta: A lightweight P2P-based cache system for model distributions on Kubernetes.
• PR-Copilot: An AI pair programmer specialized in code review, code summary and code completion.

All kinds of contributions are welcomed to the community, like PRs, issues, new ideas, documentations and more.

If you have made multiple contributions to the community or projects, enough to demonstrate an ongoing and long-term commitment to the community, please Open an issue against the InftyAI/community repo to join us.

We also have an official fundraising venue through OpenCollective. We'll use the fund transparently to support the development, maintenance, and adoption of our community.

Welcome to join us!