How AI Agent Memory Works

A language model on its own is stateless. You feed it a prompt, you get back a continuation, and the moment the response is finished the model forgets you ever existed. There is no “previous conversation” living inside the weights.

An agent, by contrast, is the orchestration around the model: a loop that decides what context to pass in next. Memory is the part of that loop that carries information forward. Everything in this essay is a different answer to the same question, what should we put in the prompt this time?

Before we discuss anything fancy, let's acknowledge the simplest kind of memory there is: just keep stuffing the whole transcript back into the prompt every turn. As long as everything fits, the model has perfect recall.

The catch is the ceiling. Every model has a fixed context window. Once your conversation outgrows it, you have to drop something. The naive policy is FIFO: drop the oldest turn first. Watch what happens when you keep typing.

FIFO is the simplest possible policy. It's also the worst when the dropped turn happens to contain the user's name. Real systems do better, summarization, retrieval, hierarchical paging. We'll get to those.

At any given moment your agent is juggling two very different things. On one side: the live conversation, recent turns, pending tool calls, whatever the model is actively reasoning over. On the other: everything it has ever decided was worth keeping.

The handoff between them is where most of the interesting design happens. What gets encoded? When? At what granularity? Drag a message across the divide, or tap encode → on a desktop without drag support, to commit it to long-term memory.

In a real system the agent decides this for itself, usually by prompting another model with a question like “is this turn worth remembering?”. Self-editing memory architectures push further, letting the agent edit its own long-term store on the fly. Section 7 compares those approaches side by side.

Lifecycle, not storage

When writes conflict.

Memory is a lifecycle problem: write, age, supersede, redact, forget. Watch the same input handled three different ways.

Incoming utterance

User lives in Istanbul. User is moving to Berlin next month. User's credit card number is 1234-5678-9012-3456.

An embedding is a vector, a list of numbers, produced by running text through a neural network trained for one purpose: put similar meanings near each other. Real embeddings usually live in hundreds to thousands of dimensions; OpenAI's current text embeddings default to 1,536 or 3,072 dimensions. Visualizing those is impossible, so this toy demo projects to two.

The plot below contains a fictional user's memories, clustered by topic. Type a question. The query gets embedded the same way and placed on the plot. The closest points, measured by cosine similarity , are what the agent would retrieve.

The 2-D layout here is a deliberate cartoon. Real embedding models place these vectors in spaces with thousands of dimensions, where many independent “axes of meaning” can coexist without crowding each other. Cosine similarity, though, works the same way regardless of dimension, which is why the trick scales.

Cognitive science has been carving up “memory” for a century. Modern agent frameworks borrow the same vocabulary because the distinctions are actually useful: each kind has a different shape, a different write rule, and a different retrieval strategy.

Click each card to see a toy version of how that store works.

Everything from the previous sections clicks together here. RAG is the loop most production agents run on every turn: receive the user's message, encode it, find similar memories, splice them into the prompt, generate, and, only when the user introduced something new, decide what is worth remembering.

Each stage in the loop is a place where you can spend engineering budget. Better embeddings, smarter retrieval, prompt compression, stricter governance, they're all the same pipeline, just with more care taken at one step.

Hypothetical Document Embeddings

A question and its answer are different shapes. Embedding the question directly often misses documents that contain the answer.

HyDE asks the LLM to produce a hypothetical answer first, embeds that, then searches. The fake answer doesn't need to be correct, just shaped like the retrieval target.

trace

Production retrieval is a small pipeline running on every turn: decide if you even need memory, rewrite the query, run several retrievers in parallel, merge their rankings, rerank, apply permission and temporal filters, then pack what survives into the prompt. Skipping any one of these stages is usually how things break.

If retrieval is warranted, you almost never want to pick a single retriever. Dense embeddings are great for paraphrase and intent; lexical (BM25) wins on exact IDs and rare tokens; a knowledge graph contributes structural answers. Run all three and fuse the rankings with RRF.

Same query, different stages, same outcome rarely. The interesting bugs are downstream: a retriever that's technically correct produces a memory that's outdated, or scoped wrong, or fine on its own but contradicts another retrieved row. Filters and rerank exist for those cases.

Most production agents end up combining several of these, a vector store for semantic recall, a graph for structured facts, a governance layer that handles supersession and PII. The matrix below separates what the architecture gives you directly from what needs a metadata or policy layer.

A single agent only has to answer “what do I remember?”. As soon as you have a team, the question becomes: which agent remembers which fact, on whose behalf, and who else can read it. Memory turns into a graph of stores with scopes, permissions, and propagation rules.

The default should be the opposite of the easy thing: private memory by default, shared memory explicit. A research note the Researcher agent jots down for itself does not need to land in the project channel. Cross-scope writes should be a deliberate act, with a policy attached.

The interesting failure modes aren't “the agent forgot” anymore. They're things like the wrong agent remembered the wrong thing on someone else's behalf. Six patterns show up over and over:

Frameworks like AutoGen, CrewAI, and LangGraph each give you the plumbing, checkpoints, persistence, message-passing primitives. None of them decide your governance for you. Scope, policy, ingestion, and evaluation are still yours.

Adding memory to a real product is not “install a vector DB.” You need an API surface, separate read and write paths, background extractors, multi-tenant isolation, latency budgets, observability, and a plan for the day you change your embedding model. The list is long because production is long.

Two services, sharply separated: the agent runtime on the request path, and the memory service as a side-quest. Background workers do the slow, expensive work - extraction, summarization, re-embedding, decay, without blocking the user.

The other axis is time. Memory retrieval runs on eligible turns, so every millisecond on that path shows up in p95. The interesting optimizations aren't the obvious ones, they're things like skipping retrieval entirely on queries that don't need it, caching the top-N facts per user in a KV, and running the dense, sparse and graph retrievers in parallel rather than sequentially.

None of this is exotic, it's the same architecture you'd build for any retrieval product. The lesson is just that agent memory is a retrieval product, not a feature flag. Treat it like one and the rest follows.

Work in progress — more features coming

Everything in this essay collapses into a small set of knobs. Choose a backend, set the limits, flip on the techniques you trust. Send a message and watch each stage of the pipeline fire, retrieval, generation, governance, write.

Try this: send the same question with the governance gate off, then turn it on and send a contradicting fact. The inspector will show old entries marked supersededinstead of being overwritten, and the credit-card pattern never makes it past the gate.