App coming soon
Your old PCs, working overnight.
A private queue for the computers already in your house. Ask at bedtime, read the answer at breakfast. No terminal, no monthly bill, nothing leaving the building.
- 21:40
You ask
Type the job on your phone, on the sofa. Summarise these forty pages. No settings to pick.
- 23:10
The house works
The office PC is idle, so it takes the job. Nothing leaves the building and no meter is running.
- 06:30
It is waiting
The answer is in your inbox before the kettle boils. Slower than a rented model. Yours.
- Runs on
- macOS, Windows, Linux
- Setup on day one
- One question, then done
- Your data
- Stays on your machines
Setting up
We look at the machine. Then we ask one thing.
On first launch it builds a picture of the computer in under two seconds. Then it asks what else you normally use this machine for. That is the whole of day one — there is no model list, and no numbers to look up.
The one question
What else usually runs on this computer?
- Just this appIt can use everything
- A few thingsLeave about half free
- A lotBe gentle, leave most free
Your office PC can run a 7B model at about 18 tokens a second — good for summaries and drafts. Link a second machine and the pool can take more kinds of job.
What it can do
What the machines can do together
Linking machines widens which jobs you can accept, and makes it likelier one is awake. It does not run one giant model across your laptops — each job runs on a single machine that fits it.
Chat and summarize
In v1- Needs
- Text model, about 4 GB
- Your machines
- Yes. Office PC
Translate
In v1- Needs
- Text model
- Your machines
- Yes. Either machine
Generate images
Later- Needs
- Diffusion model, about 6 GB
- Your machines
- Needs an extension
Clean audio
Later- Needs
- Audio model, about 2 GB
- Your machines
- Needs an extension
Create courses
Later- Needs
- Text + long context
- Your machines
- Needs an extension
Every morning
The phone is the inbox, not the computer
Submit a job, go to sleep, read the answer in the morning. The work ran on a machine in your house — not in a rented model, and not on the phone in your hand.
- Slower than ChatGPTIt runs on a home PC. It is not pretending otherwise.
- PrivateThe job never leaves the house. Nothing is uploaded to be read.
- Free after $29One payment. No monthly bill, ever.
Pricing
$29
once, then never again
$29 once. Local-first. No terminal. No monthly bill. Not a subscription and not affiliated with the LocalAI open-source project.
Questions
The things people ask
Is this the LocalAI open-source project?
No. 1LocalAITool is a StoicSoft household product. It is not affiliated with LocalAI. We market the keyword local AI. The product name is 1LocalAITool.
Do I need a terminal?
No. The happy path is machines, jobs, and morning results. Advanced exists. It is not day one.
Is it as fast as ChatGPT?
Slower than ChatGPT. Free forever after $29. Private. Ready by morning. Speed estimates come from a real benchmark on that machine, cached, not a marketing number.
If I link two PCs, do they run one giant model together?
No. Each job runs on one awake machine that fits the model. Linking increases what kinds of jobs you can accept and how often a worker is awake. It does not invent a cluster speed.
What is the price?
$29 one-time. No monthly bill.
App coming soon
Put the spare computer back to work.
1LocalAITool is pre-launch. Join the waitlist for the first builds and for the $29 one-time licence when it opens.