Preview on Agent Mesh

Sandboxed agents

Mon, 01 Jan 0001 00:00:00 +0000

An autonomous agent runs untrusted or model-generated code and prompts. To run one safely, you need two things that work together:

OS and network confinement, provided by a dedicated sandbox runtime (NVIDIA OpenShell, Kubernetes agent-sandbox with gVisor or Kata, or Docker Sandbox docker sbx), so the process can only talk to the local gateway.
Task-scoped authorization and credential brokering, provided by Agent Mesh (agentmesh-node or agentgateway + agentmesh-node), so the sandbox never holds a standing cloud credential or ambient workload token and can only call the services, MCP tools, HTTP paths, and cloud resources permitted for its current task.

This page shows the four deployment blueprints for connecting sandboxed agents and multi-hop sub-agents to an Agent Mesh.

Agent architecture

Mon, 01 Jan 0001 00:00:00 +0000

This page explains how Agent Mesh authenticates workloads and users, scopes authority to individual tasks and sub-agent hops, integrates with existing gateways and sandbox runtimes, and brokers short-lived credentials to external cloud APIs without placing standing cloud credentials inside the agent environment.

A courier network for tasks

Agent Mesh moves tasks between environments that trust nothing on arrival, the way a courier network moves parcels between post offices:

Agent Mesh Connect (Android)

Mon, 01 Jan 0001 00:00:00 +0000

Preview

Agent Mesh Connect currently supports Android only. There is no iOS app. The app is tested in CI on an Android emulator. Its screens, the on-device tools it exposes and the FFI surface may change.

Agent Mesh Connect is a Flutter app that runs agentmesh-node on an Android phone. The Go node is compiled into a shared library and driven over Dart FFI. The app is the UI around it, plus a small MCP server that exposes the phone’s sensors to the mesh. A phone enrolled this way is a node like any other. It has a key, a credential and a peer ID, and it appears in discovery with its phone-sensors service.

Scale report: what an agent costs

Mon, 01 Jan 0001 00:00:00 +0000

Preview

These measurements are of the sandbox datapath described in Sandboxed agents. They were recorded on 2026-08-21 at commit e5b2966, when the boundary spoke SOCKS5. The boundary has since moved to HTTP CONNECT and has not been measured again. The shape of the results is what matters. Single figures are indicative.

The design gives every agent its own boundary, which resolves names and enforces policy on each flow. That sounds expensive. This page measures it. The method is written down so that the result can be challenged, and a script is provided so that it can be run again. There are two experiments: a sweep of boundaries attached to one node, and a thousand agents in microVMs on one host.

Scale experiment: reproducing the thousand-agent run

Mon, 01 Jan 0001 00:00:00 +0000

Preview

The scripts under tests/scale/ and scripts/ are research tooling for the scale report. They are kept working but are not a supported product surface.

The report says what was measured and what it means. This page says how to run it again. The setup is one host, one agentmesh-node, and N agents. Each agent is a Firecracker microVM with no network device, and its only way out is a vsock to its own agentmesh-box. A thousand agents have been run on one n2-standard-64.