iSNEPS
iSneps is one personal AI with one memory — the same assistant in Telegram, on the web, on your desktop, and inside your Obsidian vault. Tell it something in one place, ask about it in another.
No installs, no setup — sign in and it is yours.
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.
Read a document. Took an action. Remembered — in a different app, two days later.
Same assistant everywhere, but it knows where it is. Your notes are reachable in Obsidian and not in a group chat.
Your digital life, filed. Documents, PDFs — scanned ones too — email, photos, and voice notes. It reads them, files them, and you can ask questions across all of it.
Summarize the PDF I uploaded yesterday
The people in your life. A people graph with face recognition — it connects who's who across everything you've given it.
Find photos of Sarah
It does things. Searches the web, controls your smart home, sets reminders and calendar events, reads and sends email, generates images, and can speak its replies aloud.
Turn off the living room lights
Deep research. Ask a hard question and it dispatches a research team that returns a cited report, saved to your library.
Compare the top three local LLM inference engines
A personal newspaper. A live news feed built fresh each time you open it, shaped by what you actually read.
What's in my news this morning?
Health-aware. It reads your Oura ring — ask about last night's sleep or this week's readiness trend.
110+ built-in abilities · 11 LLM providers with automatic failover · 7 Telegram Mini Apps · 13 Obsidian vault tools
Your conversations, files, and memory live in per-user databases scoped to your account — not pooled, not shared. Prefer your own hardware? A desktop edition that runs everything on your machine is in beta.
It speaks to 11 chat providers — Gemini, Claude, OpenAI, Grok, and more — with automatic failover. Ollama support can run inference on local hardware as well.
For developers: an OpenAI-compatible endpoint (/v1/chat/completions) lets any OpenAI SDK point at your iSneps.