Google open-sources AX, a Kubernetes-style orchestrator for billions of AI agent tasks
thisdudelikesAI · x · 2026-10-16
Google open-sourced AX, a high-throughput declarative orchestrator for autonomous AI agent workloads—think Kubernetes for agents—built on Agent Substrate for sandboxed execution and designed to run billions of tasks per cluster.
Key points:
- Rationale: agents are a new workload class—not stateless microservices or batch jobs; they accumulate state, need strict isolation, call model APIs and tools nonstop, and can burn money in loops unattended.
- Workflow: declare task, workspace, and model in one YAML; AX spins up a sandbox wired with Git repos, MCP servers, and skills; ax apply launches, ax ssh shells into a running agent, ax suspend/ax resume pause and resume exactly where it left off.
- kubectl users will feel at home. Apache-2.0 licensed; still in heavy development with likely breaking changes before a stable release.
More from coding & agent
- Founder wipes 30k lines of tech debt in one shot with Opus — lucasmeijer · 2026-10-16
- Japanese engineer runs an AI agent org inside tmux: per-project teams, one human talking to the orchestrator — 4310sy · 2026-10-16
- gloria-mcp ships an MCP server serving Gloria AI's curated crypto news — modelcontextprotocol · 2026-10-16
- Pine Script MCP server lets AI agents read v6 docs and validate syntax — modelcontextprotocol · 2026-10-16
- Open-source ebook2audiobook turns any ebook into a free audiobook, 20.4k GitHub stars — thisguyknowsai · 2026-10-16
- Composing music with math patterns via Gemini agents in Antigravity CLI — fofrAI · 2026-10-16