Search IT Labs India

Didn't find it? Ask in plain words. Ask us a question
NectarBoxby IT Labs India
In testingNectarBox by IT Labs India

Updated

Use AI on your own data without sending it out.

Your apps and bots call one address. The answers come from models that run in house, not from a cloud AI company.

Register your interest All features →
app bot script IN HOUSE · YOUR SERVER one address private models nothing sent to a cloud AI company

Who it is for, and the problem

Teams that handle other people’s data and still want AI: agencies, law firms, accountants and in-house teams that run several AI-driven apps.

  1. 01Using AI on client data usually means sending it to an outside AI company.
  2. 02Every app has its own AI key, so nobody can say who used what, or switch one off safely.
  3. 03One client’s data must never show up in work for another.

How it works

FIG. 2 · WHERE A REQUEST GOESONE CALL, STEP BY STEP
NectarBox · local models only in version 1 01 Your app Any app, scriptor bot, with itsown key 02 The door One address,the standardchat request 03 Who are you The key ischecked, theperson found 04 Record Who, which model,how many tokens.No text by default 05 Local model The model on yourbox answersthe call The answer goes back to the app and usage is counted NectarBox · local models only 01 Your app Any app, script or bot with its own key 02 The door One address, the standard chat request 03 Who are you The key is checked and the person found 04 Record Who, which model, how many tokens 05 Local model The model on your box answers The answer goes back to the app and usage is counted.

Every call passes the same few checks in the same order. Only the door is open to your apps; the model is never reached directly. In version 1 only local models answer.

Main features

All features →
Standard chat APIReady

Apps that already speak the common chat API work by changing only the address and the key.

Its own key for each app, script or botReady

Each AI call is tied to one person's key. Showing the app name for keys made on IT-Labs Core is still being built.

Private models onlyReady

Your text is answered on our own model servers and is not sent to an outside AI company.

Client wallsReady

Built so that one client's requests, records and costs never reach another client.

No text stored unless you switch it onReady

By default only who, when and how much is kept, never the prompts or answers.

Usage per app and per personReady

See calls and volume per key on the Usage page; app names for IT-Labs Core keys are still being built.

Ready: built and passing its tests on our development system. In testing: built and in testing; anything that does not pass testing will be removed. Nothing is in customer use yet.

Security and where your data lives

  1. 01In version 1 every answer comes from a model on the server set up for you. No text is sent to a cloud AI provider.
  2. 02Prompts and answers are not stored unless your organisation and that app’s key both switch the log on. By default only who, which model, how many tokens and when are kept.
  3. 03Each app has its own key, shown once. Keys can be suspended or revoked without touching other apps.
  4. 04Records are fenced by person and by client in the database itself. Our staff manage accounts and seats and are built not to read your prompts or answers; checked by our own tests; not independently audited.
  5. 05People sign in with a passkey, not a password.

NectarBox is in testing. It has not been independently audited, and we claim no compliance certification.

Works with

BeeBoxAI agents can use it as their model door (planned) The AI Hivecan use it for its own model work (planned) HiveGatemail summaries and reply drafts (planned)

Any other app that speaks the standard chat API format can call it too.

What you need to run it

A server that can run small open AI models. We decide the size with you: it depends on which models you want and how fast answers must be. On our test box, small models run on an ordinary server processor, and an answer takes from a few seconds to about a minute.

A server with a dedicated graphics processor would give faster answers and room for larger models.

Version 1 runs on our test box today. Running NectarBox as a private AI box in IT Labs India’s cloud or on your premises is the plan for a pilot; sign-in is moving to IT-Labs Core.

How a pilot would work

Cost is scoped per pilot. Talk to us.
  1. 01Talk to us. Tell us which apps, bots or scripts should use AI, and what data they handle.
  2. 02We set up the box. We set up NectarBox and the local models with you, with your organisation.
  3. 03People join. Each person gets a seat and a welcome link, and makes a passkey instead of a password.
  4. 04Apps connect. People make a key for each app or bot and change its address and key. The app is otherwise unchanged.
  5. 05We review together. You see usage by person and app, and decide what to keep.
FIG. 3 · FROM A SEAT TO THE FIRST CALLDASHED = BEING BUILT
01 A seat is added Set up from yourIT Labs India accountfor one person 02 Welcome mail A one-time linkthat expires,sent by mail 03 Sign-in The person makesa passkey, withno password 04 First use Make a key for anapp and copy theexample call 01 A seat is added Set up from your IT Labs India account 02 Welcome mail A one-time link that expires 03 Sign-in A passkey, with no password 04 First use Make a key and copy the example call

Ready today

Built and in testing

Nothing is marked “Available now” yet. Version 1 runs on our test box. Built and in testing. Anything that does not pass testing will be removed.

  • In testingStandard chat door
  • In testingA key for every app or bot
  • In testingLocal models only
  • In testingClient walls
  • In testingText log only when switched on
  • In testingUsage per person, app and organisation
  • In testingPasskey sign-in and welcome link

Interested in NectarBox?

No pilot is offered yet. Register your interest and we will tell you when one opens.

Register your interest