Open Source AI Infrastructure
AI infrastructure is the software and systems used to build, run, and manage AI applications. It supports tasks such as preparing data, serving models, coordinating workloads, and providing the compute, storage, and security these systems need. Reliable infrastructure helps teams control costs, protect sensitive information, and move AI workloads from experimentation into production.
Open source tools in this area include model-serving platforms, orchestration layers, agent runtimes, data systems, and isolated execution environments. When choosing a tool, consider its maturity, license, maintenance activity, hardware and deployment requirements, security model, and compatibility with existing services. This area is useful for developers, researchers, and organizations building or operating AI applications across local, self-hosted, and cloud environments.
4 repositories · updated September 22, 2026

HarnessRouter: Unified Interface for AI Agent Harnesses
HarnessRouter Community Edition provides a self-hosted, Apache-2.0 licensed unified interface for various AI agent harnesses like Codex, Claude Code, and Hermes. It allows users to run multiple agents through a single API, offering features such as sessions, streaming, file handling, and cancellation. The project implements the open-standard Unified Harness Protocol (UHP), ensuring users maintain control over their keys and infrastructure.

Open Index: A Deterministic Memory Layer for Your AI Agents
Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a "brain," a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.

SandBase Harness: Local-First AI Agent Runtime with Sandboxed Sessions
SandBase Harness is a local-first, self-hosted runtime for AI agents, offering sandboxed sessions, memory, and credentials. This TypeScript-based project provides a robust infrastructure for managing and observing AI agents, ensuring auditability and secure execution on your own machine or infrastructure.

Agent-Sandbox: Enterprise-Grade Sandbox for AI Agents on Kubernetes
Agent-Sandbox provides an easy-to-use, enterprise-grade sandbox platform for AI Agents. It allows agents to securely run untrusted LLM-generated code, perform browser and computer use, and deploy websites with multi-session and multi-tenant isolation. This self-hosted solution wraps a robust Kubernetes foundation behind a simple RESTful API, making it accessible for developers.