iSNEPS
Everything you are on paper — the leases, the inbox, the photos, the people — digitized into one twin that knows all of it and answers for it. No app to adopt, no platform to move into, no fees. Wherever you are, whatever the question: it's a message away.
No installs, no setup — sign in, send it something, and the twin starts forming.
This is the renewal my landlord sent over.
Read it. Twelve-month renewal, rent up 4 percent, and you have to sign by September 12. I've filed it with your housing documents — want a reminder before the deadline?
A week before.
Done — reminder set for September 5.
— two days later, in a different app —
When do I have to sign the lease?
September 12 — from the renewal you sent me on Telegram Tuesday. Your reminder is already set for the 5th.
It read a scanned lease, filed it, set the reminder — and still knew everything two days later, in a different app, unprompted.
This is what it was supposed to become. Every AI is brilliant; none of them know you — a twin has to. So iSneps ingests the actual record of your life, not a handful of facts about you, and answers across all of it at once.
And you just ask, in plain words:
Find photos of Sarah
Summarize the PDF I uploaded yesterday
How have I been sleeping this week?
A twin that only recalls is a filing cabinet. This one holds the pen.
It runs the errand inside the conversation. Sets reminders and calendar events, reads and sends email, controls your smart home, searches the web, generates images, and can speak its replies aloud.
Turn off the living room lights
It fields a research team. Ask a hard question and it dispatches multiple experts who come back with a cited report — saved to your library, where it becomes part of what it knows about you.
Compare the top three local LLM inference engines
It edits you a newspaper. A live personal news feed, built fresh every time you open it and shaped by what you actually read — not what a platform wants you to see.
What's in my news this morning?
110+ built-in abilities · 11 LLM providers with automatic failover · 7 Telegram Mini Apps · 13 Obsidian vault tools
There is no iSneps world to move your life into. The twin lives behind whatever you already use — tell it something in one place, ask in another, and it has already caught up. Statuses below are literal — Live is usable today, Beta runs with rough edges, Experimental works but is not under active development.
Your conversations, files, and memory live in per-user databases scoped to your account — not pooled, not shared.
The memory is permanent; the intelligence behind it is swappable. iSneps speaks to 11 LLM providers — Gemini, Claude, OpenAI, Grok, and more — with automatic failover, and Ollama support can run inference on local hardware.
The platform behind iSneps is packaged as snepkit — an open-source (MIT) kit that stands up essentially the whole web platform on your own hardware, with your own keys: the bots, the chat, the tools, the memory. Public release is in preparation. A Windows desktop edition of iSneps itself is also in beta.
For developers: an OpenAI-compatible endpoint (/v1/chat/completions) lets any OpenAI SDK point at your iSneps.
Send it something today. Ask about it anywhere, any day after. Your twin will already know.