• TrueNAS
  • Wren AI

TrueNAS × Wren AI

Private GenBI on storage you already trust.

Wren AI runs inside your network, next to the data you keep on TrueNAS. Your team and your AI agents ask in plain language, a local model writes the SQL, and nothing leaves the building.

  • No data migration
  • Fully air-gapped option
  • Snapshots and replication
Private deployment online
Your network
  1. People and AI agents ask

    Your team
    • Slack
    • Microsoft Teams
    • MCP agents
  2. Governed GenBI agent and context layer

    Wren AI
    • Context model (MDL)
    • RLS and CLS
    • Validated SQL
    • Audit logs
  3. Local model endpoint

    Your GPUs
    • Ollama
    • vLLM
  4. Enterprise storage and data protection

    TrueNAS
    • OpenZFS
    • Snapshots
    • Replication
    • NFS, SMB, iSCSI, S3
Air-gap ready
No metered APIs
Zero data egress
Bytes sent outside your network
0
Data sources, queried in place
20+
Enforced before any query runs
RLS + CLS
Users, session-based license
Unlimited

Who brings what

Storage keeps the data. Wren AI makes it answer.

Two layers with one job each, inside one network boundary.

TrueNAS

Storage layer

Enterprise storage and data protection.

TrueNAS holds the datasets your databases and engines read, and everything the GenBI agent writes, on OpenZFS storage you operate.

  • OpenZFS with end-to-end checksums
  • Snapshots you can roll back to
  • Replication to a second system
  • File, block, and S3-compatible object access
Wren AI

GenBI layer

Governed answers for people and AI agents.

Wren AI reads your schema, builds the context model, and answers plain-language questions with SQL you can inspect.

  • One context layer for your team and your agents
  • Row- and column-level security
  • Validated SQL and a full audit trail
  • Local models, no cloud LLM

How a question flows

The model goes to the data, not the other way around.

A question is asked, grounded in your business definitions, answered by a local model, and run against data that never left TrueNAS.

Private deployment boundary
Your network
Standalone or KubernetesAir-gap ready

Storage

Data on TrueNAS

Databases, files, and object data stay on your TrueNAS storage and are queried in place.

No ETL, no migration

GenBI

Wren AI

Grounds every question in your schema, metrics, and permissions before any SQL runs.

Governed context layer

Inference

Local model

A validated open-weight model served by Ollama or vLLM, or delivered on the Phison AI Data Platform.

Your GPUs
External AI APIs
Egress blocked by design
Blocked
0outbound calls
0prompts shared
0tokens metered
01

Nothing to migrate

Wren AI connects to the databases you already run. The data stays where your storage team put it.

02

Air-gap ready

The agent, the context layer, and the model all run on networks with no internet route.

03

Governed by default

Permission-aware SQL and audit logs keep every answer inside policy, for people and AI agents alike.

Data protection

What the agent learns is worth protecting.

A GenBI agent does more than read. It writes the definitions, memory, and logs your company comes to rely on. On TrueNAS they get the same protection as the data itself.

01Context model
What it holdsMetric definitions, joins, and access rules: the map of how your business runs.
On TrueNASSnapshot before every change. A bad edit rolls back to the last good version.
02Memory and skills
What it holdsWhat the agent learns from daily use, and the procedures your team saves as files.
On TrueNASReplicate to a second TrueNAS system so the knowledge outlives any one machine.
03Audit logs
What it holdsUser, timestamp, and SQL for every question asked.
On TrueNASKept on checksummed OpenZFS storage, with snapshots held for as long as your retention policy asks.
04Source data
What it holdsThe databases and files Wren AI queries in place.
On TrueNASServed from the same storage over NFS, SMB, iSCSI, or S3-compatible object access.

Snapshot, replication, and retention schedules are set in TrueNAS and scoped with your storage team during rollout.

From the SC26 announcement

Why this collaboration matters

Organizations are looking for practical ways to bring AI closer to their data while maintaining control, security, and resilience. Our collaboration with Wren AI and Phison combines trusted business intelligence, accelerated AI infrastructure, and enterprise-grade data protection into a solution that helps customers deploy private AI with confidence.
TrueNASJamila GunawardenaDirector of Solutions and Alliances, TrueNAS

Hardware partners

Start from the hardware you have.

Each solution keeps the model, the data, and the answers inside your network. Pick the one that matches what is already in your racks.

TrueNAS FAQ

TrueNAS and Wren AI, answered.

TrueNAS is the storage and data-protection layer. It holds the data your databases and engines read, plus what Wren AI writes: the context model, agent memory, skills, and audit logs. Wren AI is the GenBI layer on top that turns plain-language questions into governed, inspectable SQL.

No. The GenBI agent, the context layer, and the model all run inside your network, and data is queried in place on your storage. There are no calls to a cloud LLM, and the deployment can run fully air-gapped.

No. Wren AI works with a validated open-weight model served by an endpoint you run, such as Ollama or vLLM. If you want the model runtime delivered as a platform, see the Phison + TrueNAS + Wren AI stack.

Wren AI connects to 20+ data sources, including Postgres, MySQL, ClickHouse, and DuckDB, and queries them in place with no ETL and no migration.

Request a demo. We walk your data, storage, and security teams through the architecture and scope a proof of concept on your own schema.

Architecture review

Keep the data where it is. Start asking it questions.

We'll walk your data, storage, and security teams through Wren AI on TrueNAS, and scope a proof of concept on your own schema.