Architecture · How it works
Olivares AI runs where your agents run. It deploys as a single self-hosted artifact, discovers passively without sitting in the request path, and the control plane is built to run fully air-gapped. This is how the pieces fit together. Air-gapped install and offline updates are Enterprise; the Helm chart, the Kubernetes operator and the Terraform provider are Business.
How it runs
Install the engine as a single self-hosted artifact — a binary, a container or on Kubernetes. The web console comes embedded; there is no separate front-end to stand up.
Place collectors inside your own infrastructure. They passively ingest the OpenTelemetry your agents emit and read the native audit trails of the systems they touch — read-first, minimum-privilege, push-only.
The platform normalizes those signals into a model of agents, sessions, models, MCP servers, resources and identities — and the access edges between them, read or read/write, each with an honest confidence level.
On that map, see the gap between what an agent is permitted to access and what it was observed accessing, enforce policy, and route findings to the tools you already run — all via CLI, API and the web console.
The console, CLI and API send requests to the engine. Identity, permissions and policy determine access. Admitted sessions use configured provider drivers; the engine records their state and lifecycle audit events in SQLite or PostgreSQL.
Community has no core license gate. Commercial modules add separate capabilities. Tool enforcement depends on the integration.
How it is built
The collectors run inside your own infrastructure and capture edges and relationships — not payloads. The control plane is self-hosted (a managed option is on the roadmap). Governance data — inventory, access map, policy state and audit evidence — stays in infrastructure you control by default.
The engine is CLI-first and exposes its full functionality through a stable API; the web console is a layer over that same API, shipped embedded. You deploy one thing, not a fleet of services.
It listens to telemetry your agents already emit and reads native audit trails, instead of intercepting traffic. A stable, Apache-2.0 connector SDK covers a growing set of sources — models and providers, runtimes, data stores, identity and secrets, observability, and output destinations.
It ingests OTLP telemetry and interoperates with the observability stack you already run — exposing standard metrics and health endpoints and exporting to common SIEM formats. It slots into your pipelines instead of replacing them.
The self-hosted control plane can run in an isolated network. Verify release artifacts before transferring them: keyless Sigstore and SLSA checks need network access. Operator-key checks cover only files signed with that key. Hosted models still reach their provider API; only models you host can run fully offline. Air-gapped install and offline update bundles are Enterprise.
Read-first and asymmetric-low-risk. Collectors are push-only with no inbound listener, traffic to the core is mutually authenticated with TLS, only the minimum data is kept, the audit trail is append-only and tamper-evident, and multi-tenant isolation is built into the model from day one.
Diagram labels are in English. The descriptions provide the complete reading path on smaller screens.
Deployment
The same product, deployed the way your environment needs it.
The engine and the embedded web console as one self-hosted artifact — a binary or container, or installed on Kubernetes — for a single node.
Collectors across many hosts feeding a central control plane with an external database, for multi-host scale and multi-tenant operation.
The control plane and collectors run locally with zero egress and offline licensing, for disconnected, regulated or classified networks. Agents on hosted models still need outbound access to their provider; agents on self-hostable models run fully offline.
The control plane hosted by us — while the collectors always remain inside your own infrastructure.
Capabilities and deployment options depend on the edition and your configuration; the documentation describes each one.
Self-host Community, the complete product for one person or one team, on your own infrastructure, or talk to us about a distributed or air-gapped deployment. Air-gapped install is Enterprise.