Giving a Telegram bot long-term memory with SQLite and local embeddings

One thing cloud chatbots do badly is remember you. Each session starts from zero. When I built Avelina, a self-hosted personal AI assistant that lives in Telegram, persistent memory was the whole point. Here is the architecture I landed on — all local, no external vector DB.

The problem: statelessness

An LLM call is stateless. To make an assistant that actually knows your history, you need to store facts across sessions and retrieve the relevant ones on every turn. For a self-hosted AI assistant you also want this to run on a cheap VPS with no third-party services.

Storage: plain SQLite

I keep several tables in a local SQLite database:

Giving a Telegram bot long-term memory with SQLite and local embeddings

Related reading

Building a Slack Bot That Actually Remembers: slacktag-oss

Memoria – A Self‑Evolving Personal AI with Human‑like Memory

Stateful AI without a database: threads and assistants

What I Learned About Memory-Augmented AI Agents

Give your AI memory in one parameter

Building MemBot AI: Creating a Customer Support Assistant with Persistent Memory