Agent Memory Simulator
Models don't remember anything, memory is engineered around them. Step through a conversation and watch a sliding window, a summary buffer, and retrieval keep or drop facts, and see exactly what the model sees each turn.
The thing everyone gets wrong about AI memory
A model is stateless. It doesn’t remember your last message, or the last thousand, every turn, your app re-sends whatever history fits and the model reads it fresh. So “memory” isn’t something the model has; it’s something you engineer by deciding what to put back into the context window each time. This simulator shows three common strategies and, crucially, what each one forgets.
The three strategies here
- Sliding window keeps the last N messages verbatim. Simple, but anything older just falls off, including important facts.
- + Summary compresses the dropped messages into a running summary. Cheaper than keeping everything, but a summary can blur or lose a specific detail.
- + Retrieval stores facts and pulls the relevant ones back into context when they matter, the same idea as RAG, applied to memory. The most reliable way to keep a specific fact alive across a long chat.
Pin a message as a fact (the ☆) to make it eligible for retrieval. Real systems match facts by meaning using embeddings; here we approximate with keyword overlap to keep it transparent. The summary block stands for “these turns were compressed”, in production an LLM writes it. Everything runs in your browser.
FAQ
Does the model really not remember?
Correct. Each API call is independent. Any continuity you see is your application re-sending history (or a summary, or retrieved facts) every single turn. Take that away and the model is a blank slate.
Why did the window strategy “forget” my allergy?
Because that message scrolled out of the last N. A pure sliding window has no idea a dropped message mattered. Retrieval fixes exactly this by storing facts and pulling them back when relevant.
Is anything uploaded?
No. The simulation is entirely client-side, so your conversation stays on your device.
Related
Read what agent memory is, how RAG and embeddings power retrieval, or size a window with the Context Window Visualizer.