Recall: When AI Chatbot Memory Needs to Know What’s Still Valid

A developer built Recall, an open-source Telegram bot that tracks the validity of group-chat commitments rather than merely retrieving past messages. Recall structures commitments into four event types — DECISION, COMMITMENT, AMENDMENT, and COMPLETION — and pairs a memory store with a State Resolver that determines which information is still active, addressing cases where a later message supersedes an earlier one. The project's stated principle is "The group decides. Recall remembers. Walrus proves.

Standard AI chatbots can recall past conversations, but retrieving stored data isn't the same as knowing which piece of information is currently valid. We built Recall, an open-source Telegram bot, to solve this exact problem for group chats. The Problem: Groups Change Their Minds Consider a team discussing a deadline in a busy chat: — "I will send the proposal by Friday." two days later — "Actually, I'll send it on Saturday." A simple vector or memory lookup retrieves both messages. But raw retrieval only surfaces historical facts—it cannot tell you that Saturday is the active agreement, leading standard models to hallucinate or get confused. How Recall Works Operating as a Telegram bot @Recall bot , Recall structures group commitments into four distinct event types: DECISION, COMMITMENT, AMENDMENT, and COMPLETION. Its architecture rests on three core components: Key Takeaway • Recall answers: "What was stored?" • The State Resolver answers: "What is still valid?" "The group decides. Recall remembers. Walrus proves."