Private AI you can prove, run, and put to work
Open software you control. Proof, Arena, and Relay lead: prove which AI to trust, drive the shelf of models you own, then put the winner to work. Advisor, Cortex, the API, and the apps carry the same rule: your data stays local.
Our lead products, the line you buy: prove which AI to trust, drive the shelf of models you own to find the one that wins, then put that winner to work. Advisor and Cortex round out the Arena stack.
Orionfold Proof
The tool behind the receipts. It runs on your own machine, points at your own task, and tries each AI model or setup you are weighing. It scores them on a rubric you set and hands back a signed receipt: which one won, at what cost, with what failures. Rerun it any time.
Orionfold Arena
One screen to run, compare, score, and now train the AI models on your own desktop. Watch live speed and memory, rank models on a private leaderboard, queue tests and training runs, and wake up to a morning report. Nothing you type leaves your machine.
Orionfold Relay
The operations layer for AI builders and small services teams. Run your agents from one place, across local and cloud models, send every result through your approval, and watch each client’s cost add up on its own. The free engine installs with npm; a license unlocks the premium packs you own.
The Arena stack and the core: a governed advisor over your documents, the memory it answers from, and the API to drive it all with code.
Orionfold Advisor
A local AI advisor over your own body of documents. Every answer names the exact source it came from. If your documents cannot support an answer, it refuses instead of guessing. Every check it passed is a saved receipt you can re-run.
Orionfold Cortex
A second brain that lives on your own desktop. It indexes your notes, stamps where every fact came from, and grades its own memory: a rebuild that would make recall worse is caught, not shipped. Your documents never leave your machine.
AI Native API
Drive the whole platform with code. Your own apps can start tasks, read results, and manage everything through plain web calls. It covers more than 120 calls across 26 areas of the platform.
For builders: testing, terminals, and reusable patterns.
fieldkit
A Python toolbox of patterns we proved on a small AI desktop. It covers the whole job: faster replies, search over your own files, scoring, training, and shipping models. Use just the parts you need.
Command
Turn your terminal into a fast personal AI app that runs 15+ models, including private ones on your laptop, with three simple commands.
Sentinel
Build and run tests for your AI helpers by dragging boxes around. Like Postman, but for checking that AI agents behave.
Ready-to-use apps that keep your data on your machine.
NeoCash
A money helper that runs on your own machine and walks you through taxes, saving, and investing. Your financial details never leave your browser.
OpenVolo
Keep your contacts and posts for X, LinkedIn, and Gmail in one place on your own computer, with AI helpers that draft and sort your outreach.
Memo
A Chrome add-on that saves anything you find online so you can chat with it later, using the AI you choose, even a private one on your machine.
Marketer
Turn one article into ready-to-post social updates with AI, then copy and paste them anywhere. No logins or connections to set up.
Tools that turn the fast-moving AI world into clear answers.
neosignal
See where AI is headed. neosignal tracks and scores AI models, chips, cloud hosts, and tools, then shows how well they work together. Get an alert the moment something big shifts.
Trends
AI agents research what is coming, find what your business needs, and weigh build versus buy, turning market trends into a clear tech plan.
Moments
Turns the flood of AI-industry news into clear insights, spotting the big moments and showing how they connect, all on your own systems.