Hire the model. Keep control of the work.

Agenaxy is a local-first AI agent workbench for automating real work with documents, datasets, and recurring workflows.
Some work should never end up on someone else’s server — that’s what Vault Mode is for. It works only with models you trust. An OS-level sandbox restricts the agent to approved files and folders and prevents data from being sent elsewhere, keeping every run within the boundaries you define.

Recorded in AgenaxyStandard → Vault · 5.5 seconds
Real product capture with synthetic sessions and files. The sidebar, active chat, and Session Usage panel remain visible while Standard switches to Vault; no customer or production data appears.
Who this is for

You probably need Agenaxy when the file is why you’re still doing it by hand.

Five moments you may recognize before the first run.

  1. 01

    You deleted your customers’ names and addresses before you dared hand the file to a chat.

    Hand over the whole file. The model runs on this Mac, or on a server you trust — the list never reaches an outside provider, and can’t be passed on from there.

  2. 02

    The quarter isn’t announced yet, and the reconciliation is sitting in four spreadsheets.

    Run it in Vault with a model on this Mac and the figures never leave. Nothing is sitting on someone else’s server when the announcement goes out.

  3. 03

    You’ve signed something that says “don’t paste this into a third party.”

    Use a model the paperwork already covers — one on this Mac, or a server you trust: your own deployment, or a partner the contract already names. Vault allows that one connection and closes every other route.

  4. 04

    The draft isn’t published and the interview isn’t cleared — and you’d rather neither became training data.

    Unpublished work stays a local file. Nothing is uploaded, so there is no retention policy to read and nothing to opt out of.

  5. 05

    You don’t want to give an agent write access to a folder you couldn’t rebuild.

    Every run works on a copy of your files, so the originals are never what’s at risk.

The platform way

Every device is a door into a hosted workspace. What keeps your work private there is a promise — and promises fail in ordinary ways: a bug that hands your chats to a stranger, a subprocessor you never heard of getting breached, terms that change after you agreed to them, one line of misconfiguration that puts your conversations in Google.

The Agenaxy way

The workspace is yours; the model is hired into it, task by task. Your files, chats and results never enter a hosted workspace, so none of those failures has a route to them. What holds here isn’t a policy someone has to maintain — it’s a boundary the operating system enforces.

Complete runs · different kinds of work

Hand off real work. Get an artifact you can defend.

Confidential, regulated, personal, or unpublished — the work that still gets done by hand because it can’t be sent anywhere. Each goes in with a plain-language task; a finished, source-linked artifact comes out, on your Mac.

E-commerce ops selected

Source · synthetic snapshotRecorded run
prior-week totalscurrent-week totals
Task · plain language

“Calculate the weekly changes, flag risks without inventing causes, and add two human review actions.”

Run · MiniMax M3 Free
  1. 1Prepare the task contextcontext
  2. 2Design and write the dashboardmodel
  3. 3Read back and verify totalstool
Artifact
weekly-ops-dashboard.htmlsaved locally
Recorded in Agenaxy71-second run · 8.13-second edit
Real app capture on an Apple Silicon Mac using synthetic totals. MiniMax M3 Free generated the self-contained HTML, Agenaxy wrote it locally, and the final frame is the recorded artifact — not a customer claim.
What stays · what leaves

Choose the model. Set the boundary.

Agenaxy runs in two modes. Choose a model on this Mac or on a server you trust. Standard keeps normal agent permissions; Vault allows only the model connection you chose, and stops the agent from sending your data anywhere else.

Standard · model on this Mac

The model stays local. Other routes may not.

Standard agent permissions — permitted tools or scripts may still connect.

Standard · model on someone else’s server

Task context goes to the model provider.

Standard agent permissions — task context goes to the provider; tools or scripts may still connect.

Vault · model on this Mac

Nothing leaves this Mac.

Vault rules enforced by the system sandbox — data-sending tools off, script network blocked.

Vault · model on a server you trust

Only selected context reaches the server you approved.

Vault rules enforced by the system sandbox — every route except the server you approved is blocked.

Local Workbench · system of record
  • Everything stays here. Source files, artifacts, chats, and the full run trace remain stored on this Mac in every configuration.
  • Your originals stay untouched. Every run works on a copy. Whatever the agent does, the files you started with are exactly as they were.
  • You choose what leaves. Pick a remote model for a task and it gets that task’s context — never your history, never the rest of this Mac.
Run record

Same command. Boundary included.

The probe reaches an E2E-owned endpoint in Standard. In Vault, the same shell command is denied and the failed step stays visible beside the task.

Direct boundary test · passedStandard allowed → Vault denied · 6.67 seconds
Real deterministic E2E evidence using a synthetic probe and an Agenaxy-owned local endpoint. Standard produced one network hit; Vault produced none. No customer data, credential, production endpoint, or personal path is shown.
Agenaxy for Mac

What would you put in the Vault?

Tell us about the file or workflow you need to keep under your control.

Download Agenaxy for Mac
Guides for the work behind the work

Learn the boundary. See the workflow.

Start with the concepts behind local-first agents, or jump to a complete use case for documents, finance, legal work, ecommerce, content, and small teams.

Learn

AI agent basics, private AI, Mac models, document workflows, reliability, and comparisons.

Browse learning guides →

Use cases

Concrete examples of local-first AI producing work that remains reviewable and under your control.

Browse use cases →
Would this help your work?