中文

Tokenman architecture

Tokenman is a runtime for native AI coding agents such as Claude Code and Codex, provided by model companies and run unmodified: it handles where they run, how they stay online, how people connect from any device, and how subscriptions are shared and metered. This is a conceptual map: the layers show responsibilities, not a deployment topology. The principles distinguish live behavior from work in progress.

Open the visual blueprint · Security and isolation

Four layers: clients use the hub; the hub owns central data; nodes run sessions and dial out to the hub. Model requests cross the credential proxy to external providers.

Four layers

1 · Clients

Clients connect to the hub through an encrypted entry.

2 · Application · the hub

3 · Data

Nodes initiate an encrypted connection to the hub; they do not access the data layer directly.

4 · Infrastructure · nodes that run sessions

External services

Cross-cutting concerns

How requests flow

These paths describe responsibilities. Push delivery and smooth release handover are still being completed, as marked in the principles below.

Chatting with an agent

  1. The browser opens the portal.
  2. The hub authenticates the person and finds their session.
  3. The hub relays the conversation to the node running it.
  4. Replies stream back through the hub to the browser.

An agent calls a model

  1. The agent on a node sends a model request to the credential proxy.
  2. The proxy authorizes it, chooses an eligible subscription from the pool and meters usage.
  3. The provider receives the request; its response returns through the proxy to the session.

A node stays connected

  1. The node agent initiates an encrypted outward connection to the hub.
  2. The hub delivers work and settings through that connection.
  3. The node reports state; replacing remaining polling with change notifications is in progress.

A release ships

  1. A change passes automated checks and merges.
  2. The release process publishes a verified release and deploys the hub.
  3. Nodes verify and apply their releases; seamless handover across the whole path is in progress.

Trust boundaries and data

For isolation, credential lifetimes, revocation and compromise boundaries, read Security and isolation. Repository credentials and external tool integrations have their own access boundaries; the model-key rule does not describe every secret a person may give an agent.

Design principles and why

Native agents, unmodified · live

Sessions run the official Claude Code and Codex CLIs directly and follow upstream updates, without wrapping them in a proprietary agent. Keeping the native agents intact lets people use the capabilities and workflows their model providers deliver, while Tokenman manages the runtime around them. Using a session describes the experience; there is no public deep-dive on upstream CLI updates yet.

Anytime, anywhere · live

Sessions stay on managed nodes and continue when a laptop closes. Browser, terminal and phone access let people return to the same running work from whichever device is available. Separating a session's lifetime from its client connection makes ongoing work independent of a person's device. Connecting to sessions describes access from each device.

One portal · in progress

One address should carry people from sign-in to their sessions without asking them to choose an entry point. It makes identity and navigation easier to understand while routing stays a service responsibility. Portal unification is in progress. Current member journey; there is no public deep-dive on the unified portal yet.

Nodes dial out · live

A node initiates the connection to the hub so the service can reach its sessions without requiring an inbound application port on that node. This supports both managed environments and personal machines behind ordinary network boundaries. Self-host setup and Security and isolation describe the operating and trust model.

Push, not poll · in progress

Changes should travel when they happen, avoiding repeated reads of unchanged state and keeping the hub's view fresh. Some paths still poll; this principle is a direction, not a claim that all polling has disappeared. Current service health describes today's behavior; a public push-transport deep-dive is not available yet.

Keys stay central · live

Keeping model keys out of sessions limits what an agent or a compromised working environment can take. The proxy can enforce access, select subscriptions and revoke access centrally while the session uses a scoped credential. Security and isolation explains the boundary; Subscription accounts describes administration.

Uneventful deploys · in progress

A release should preserve ongoing work and hand connections over gradually so a routine update does not become a person's interruption. Verified releases are already part of the security model; end-to-end smooth deployment is still in progress. Install and deploy and Release verification cover current operation; there is no public handover deep-dive yet.

Visible health · in progress

People should be able to tell whether a problem is theirs or the service's, using understandable health information rather than internal telemetry. A public view of that experience is still in progress. Service health documents the existing signed-in health page and its limitations; it is not a promise of a completed public status service.

Glossary

Blueprint v3 · Updated 2026-10-26. Status labels describe this version, not a delivery date.