← all releases
Google·Sep 21, 2026·v0.3.0·open source
AX
AX is a high-throughput, declarative orchestrator designed to run autonomous agent workloads at scale. It provides a sandboxed, stateful runtime that manages agent lifecycles, including sub-second suspension and resumption, to optimize compute density and cost.
featured on blogAI AgentsOrchestrationCloud NativeInfrastructure
on the blogGoogle Open-Sources AX: A Distributed Agent Runtime Built for Reliability and Resumption 4 min
overview
AX is a high-throughput, declarative orchestrator designed to run autonomous agent workloads at scale. It provides a sandboxed, stateful runtime that manages agent lifecycles, including sub-second suspension and resumption, to optimize compute density and cost.
key features
- 01Declarative task management via YAML manifests
- 02Sub-second suspend and resume for stateful agents
- 03Secure, isolated sandboxing with CPU and memory limits
- 04Generative workspace setup using plain English goals
- 05Granular network policy management and allowlisting
- 06High-density multiplexing for massive agent scaling
related productsbrowse all →
AIO Sandboxopen sourceAIO Sandbox is an integrated environment designed for AI agents, combining a browser, terminal, filesystem, VSCode, Jupyter, and MCP Server into a single Docker container. This unified setup allows seamless development and execution of AI agents without the need for multiple services.Fractalsopen sourceFractals is an open-source recursive agentic task orchestrator developed by TinyAGI. It enables the decomposition of high-level tasks into self-similar trees of executable subtasks, which are then executed by an agent swarm in isolated git worktrees.MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.