Repositoryagent-substrate/substrateTool
Autonomous agents frequently execute arbitrary code and spend substantial time waiting for tool or model responses. Substrate solves both the multi-tenant security risks and the infrastructure cost of running mostly-idle agent processes.
Rather than acting as an agent-building framework, Agent Substrate provides the underlying execution layer for platform and infrastructure engineers. By leveraging microVM isolation and fast memory snapshotting, it efficiently handles the bursty, asynchronous nature of agentic workflows. With more than 5,400 GitHub stars and an Apache-2.0 licence, it presents a mature architectural approach for enterprise-grade agent orchestration on Kubernetes.
Summary generated by AI (Gemini 3.8 Flash, 18 October 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Repository:google/ax
Google has open-sourced AX, a declarative orchestration runtime designed to manage autonomous AI agent workloads. Built on Kubernetes and Agent Substrate, it handles sandboxed execution, workspace pre-wiring, and network fencing at scale.
6.2kstarsGo
Repository:NVIDIA/OpenShell
NVIDIA OpenShell is an open-source runtime written in Rust designed to run autonomous AI agents in secure sandboxes. It enforces declarative policies at the kernel level and guards access to network routes and credentials.
16.6kstarsRust
Repository:kvcache-ai/AgentENV
AgentENV (AENV) is an open-source Rust-based platform for running isolated agent environments at scale, notably powering agentic RL training for Kimi K3.
3.4kstarsRust
Repository:anthropics/sandbox-runtime
Anthropic's Sandbox Runtime (srt) is an open-source tool designed to enforce OS-level filesystem and network restrictions on arbitrary processes. Developed as a safety component for Claude Code, it isolates AI agents, MCP servers, and shell commands without requiring containerisation.
5.1kstarsTypeScript
Repository:microsoft/mxc
Microsoft eXecution Container (MXC) is a cross-platform sandboxed code execution framework designed for running untrusted workloads such as AI model output, plugins, and tools across Windows, Linux, and macOS. It wraps native OS containment mechanisms and VMs into a unified policy engine and typed SDKs.
1.8kstarsRust
Link:Docker
Docker has expanded its platform with dedicated security capabilities for autonomous AI agents. Introducing Docker Sandboxes using microVM isolation, a centralised AI Governance console, and SLSA Level 3 Hardened Images, the platform aims to provide safe execution and compliance from local laptops to production.
Parts of this content were created with the assistance of AI.
