My AI agent remembers *when* it believed things — valid-time memory on FalkorDB

说明与用途

TimeMachine 利用 FalkorDB 存储带有效时间区间的代理信念，能够精确恢复代理在任意时间的信念，并支持“如果”情景推演。

问题

AI agents cannot answer what they believed at a past time because vector memory lacks a time axis, making audit trails impossible.

结果

TimeMachine provides exact past‑belief reconstruction and counterfactual reasoning, enabling audit‑ready AI agents that can answer time‑specific belief questions and explore alternate histories.

工作流

• Seed a fictional incident timeline into FalkorDB.
• Create BELIEVES and SUPPORTED_BY edges with valid_from/valid_to.
• When a belief changes, close the old BELIEVES edge by setting valid_to.
• Run an as‑of Cypher query to retrieve beliefs valid at a given timestamp.
• Use agent.ask() with an as_of parameter to get context‑specific answers.
• Use agent.why_changed() to trace why a belief changed.
• Use agent.timeline() to view full belief history.
• For counterfactuals, fork the graph with FalkorDB multi‑graph support, remove a piece of evidence, and recompute beliefs with agent.ask("What if …").

证据

AI agents forget. Worse — when they change their mind, the old belief is gone.

来源

TimeMachine stores agent memory as a graph in FalkorDB where every belief edge carries a validity interval

来源

When the agent changes its mind, the old BELIEVES edge is closed (valid_to gets set) — never deleted.

来源

agent.ask("What caused the checkout outage?", as_of="2026-10-08") # → connection pool exhaustion

来源

agent.ask("What if the traffic report never existed?")

来源