Memory

Persist user-specific facts, preferences, and prior context across all sessions, threads, and devices.

Keep one user's session state and memory unreachable from another user's agent.

Store memories as embeddings in a vector index and retrieve the most semantically similar items at query time.

Persist agent memory as entities and relations in a structured graph so symbolic queries (path, neighbour, type) become possible.

Choose what fits in the context window each turn given a fixed token budget.

Stage agent memory across sensory, working, short-term, episodic, and long-term tiers with explicit promotion and decay between them.

Treat the LLM context window as RAM and external storage as disk, with the model issuing tool calls to page memory in and out.

Compress past episodes into summaries that preserve gist while shedding token cost.

Record past events as time-stamped first-person experiences the agent can recall later, separately from extracted facts (semantic) and learned how-to (procedural).

Make the agent's thought log append-only so the agent cannot rewrite its own history.

Maintain a dedicated store of what the agent holds to be true about the user and the world, separate from event records (episodic) and learned how-to (procedural).

Expose memory management as first-class tool actions (ADD, UPDATE, DELETE, RETRIEVE, SUMMARY, FILTER) the LLM chooses at every step, trained end-to-end so short-term and long-term memory live under o…

Maintain a third agent memory type alongside episodic (past events) and semantic (facts): procedural memory captures *learned how-to* — reusable skills, workflows, and self-rewritten system instructi…

For reasoning models that emit a separate reasoning trace, preserve that trace in context across the same logical task episode (across tool-call/result turns) but drop it at user-turn boundaries.

Score every candidate memory item with a weighted salience function so each tick attends to a small, relevant top-k subset rather than re-reading all memory.

Ground the agent's reasoning in the current absolute time without requiring tool calls, so every reply is implicitly time-aware.

Structure inputs into digestible topical segments (chunks) before feeding to short-term memory rather than throwing the full input at the model; reduces overload and increases accuracy (~40% improvem…

Use different storage technologies optimized per memory type — fast in-memory stores (Redis-class) for episodic, vector databases (Pinecone/Weaviate) for semantic, relational or workflow engines for…

Give the agent a writable scratch space for intermediate notes that informs later turns but does not pollute the response.

Carry the relevant slice of conversation context across turns within a session.

Hold context-window utilization below a working threshold (~40%) to keep the model out of the 'dumb zone' where it begins ignoring earlier instructions and hallucinating.

Architect agent memory as three integrated concentric layers — Short-Term Memory (outer), Long-Term Memory (middle), Feedback Loops (core) — operating together as a unit rather than as separable opti…

Memory store structured as a typed entity-relation graph used as the agent's authoritative world model for planning — not only for retrieval.

Surface relevant persistent memories proactively when the human mentions a concrete entity the agent has prior knowledge of, so the human does not bear the burden of remembering to ask.

Lift archived memory items back into short-term tiers when something re-attends to them.

Long-context attention mechanism placing sparse landmark tokens across very long inputs so the model jumps directly to relevant sections via landmark lookup rather than scanning linearly.

Mine a small bounded vocabulary from the agent's own writing and cache it as the conceptual axis for scoring new thoughts, so relevance reflects the agent's actual frame rather than a generic embeddi…

During idle or downtime, run the model offline against the user's standing context to pre-compute dense summaries and likely future answers, so test-time latency and cost drop when the user actually…

Memory module that learns at inference time by incorporating recent inputs into its parameters during the session rather than relying solely on pre-trained weights.