KXO API Token Console
Create owned Agentic OS API tokens with quota context.
Core
Agentic OS landscape
The CNCF landscape works because it turns a messy ecosystem into a searchable operating map. This Agentic OS landscape does the same for teams issuing API tokens to coding agents, research agents, browser agents, and internal automations.
9
ecosystem categories
36
mapped surfaces
4
operational layers
Each section shows the surfaces a production Agentic OS API token has to coordinate. KXO sits in the access and control plane so agent code can keep one stable credential while operators adjust routing, quota, and ownership.
Reference views
Use these diagrams when explaining how Agentic OS API token access connects the ecosystem.
layer: Core access plane
Where operators issue, scope, rotate, revoke, and audit Agentic OS API token access before agents reach production.
Create owned Agentic OS API tokens with quota context.
Core
Account sessions and operator identity for the SaaS layer.
Core
Dedicated non-human identities for production agents.
Control
Copy-once token visibility and revocation history.
Control
layer: Model relay plane
The upstream model providers, fallback groups, and relay policies that sit behind a stable Agentic OS API token.
High-reasoning model access through managed routing.
Core
OpenAI-style API access for agent runtimes and SDKs.
Core
Backup model groups when a primary route is unavailable.
Control
Token-level usage accounting for spend visibility.
Control
layer: Agent runtime plane
Frameworks that turn model access into planning, tool use, delegation, memory, and multi-step agent workflows.
Graph-based agent state machines and tool loops.
Runtime
Data-aware retrieval, indexes, and agent workflows.
Runtime
Multi-agent orchestration and delegated workflows.
Runtime
Role-based agent crews for repeatable tasks.
Runtime
layer: Work execution plane
Coding, review, and terminal agents that need reliable model access, cost boundaries, and auditable work sessions.
Coding agent workflows that need stable model calls.
Delivery
Terminal-based development flows with governed access.
Delivery
IDE agent sessions with budget and routing needs.
Delivery
Automated checks and review loops in delivery pipelines.
Delivery
layer: Tool interface plane
The protocols and connectors that let agents reach files, browsers, SaaS apps, search, code, and internal systems.
Tool and context servers attached to agent runtimes.
Runtime
Computer use, browsing, capture, and web automation.
Runtime
Team workflows and notifications for agent operations.
Delivery
Repository, pull request, and issue automation surfaces.
Delivery
layer: Context plane
Vector stores, files, caches, and context registries that keep long-running agents grounded without leaking credentials.
Retrieval memory for documents, code, and knowledge.
Runtime
Durable file storage for outputs and attachments.
Delivery
Session state, queues, rate limits, and runtime caches.
Runtime
Versioned prompts for repeatable agent behavior.
Control
layer: Control plane
The dashboards, alerts, cost reviews, and traces teams need before agent work becomes expensive or opaque.
Token-level usage review for operators and teams.
Control
Spend guardrails before agents run beyond intent.
Control
Traffic analytics for public product surfaces.
Control
Readable access trails for incident and finance review.
Control
layer: Delivery plane
Where agents show up for users: internal automations, product features, customer support, research, and ops workflows.
Scheduled and event-driven automation flows.
Delivery
No-code business process automation with model calls.
Delivery
Product-facing agents with quota-aware access.
Delivery
Long-session investigation and synthesis workflows.
Delivery
layer: Infrastructure plane
Cloud and runtime infrastructure for hosting the SaaS surface, relay backend, caches, databases, and agent delivery workflows.
Global SaaS edge runtime for the public console.
Delivery
Service orchestration for relay, Redis, and MySQL.
Delivery
SaaS application data and product configuration.
Core
Persistent relay-side users, keys, quota, and usage.
Core
Agentic OS ecosystem overview
A wide map of model access, token control, runtimes, memory, tools, and delivery surfaces around one governed API token plane.
Runtime topology
A topology view showing how coding agents, research agents, browser agents, and internal automations call models through KXO.
Governance map
A control-plane diagram for ownership, quota, revocation, observability, billing, and audit trails around Agentic OS API tokens.
Create a KXO API token, attach it to the model route your agent needs, and keep quota, ownership, and revocation decisions visible from day one.