Loading course…
Building Reliable Agent Memory and Persistence
Created by Petter Smit
Design and implement memory systems for AI agents that remain coherent, debuggable, and safe under long conversations, parallelism, and failures. You will learn how to model memory layers, merge state deterministically with reducers, checkpoint and replay safely, manage context windows, and build durable long-term memory with retrieval and governance.
Requirements
- Comfort with LLM chat prompting and tool-calling agents
- Basic understanding of embeddings and semantic retrieval
- Familiarity with workflow/graph-based agent execution (nodes, state)
- Basic software reliability concepts (retries, side effects, persistence)
What you'll learn
- Design a layered memory architecture for agents, mapping each data type to the correct lifecycle and storage.
- Implement deterministic state evolution using reducers that safely merge parallel and out-of-order updates.
- Checkpoint and replay agent workflows reliably, including handling external side effects with compensation patterns.
Learning path
8 modules • Each builds on the previous one
1
Memory layers and state model
Define a practical taxonomy for agent memory: transient context, workflow state, conversational memory, retrievable knowledge, and durable long-term memory. Map each layer to storage, lifecycle, and correctness requirements in production agent systems.
1 video4 min
2
Reducers for deterministic state updates
Learn what a reducer is in agent state frameworks: a merge/update policy for each state key that turns multiple partial updates into a single next state. Emphasize determinism, idempotency, commutativity/associativity tradeoffs, and conflict resolution under parallel execution.
1 video4 min
3
Checkpointing, replay, and recovery
Design checkpointing for agent workflows: what to persist at node boundaries, how to resume after crashes, and how checkpointing enables replay/time-travel debugging. Cover tradeoffs: granularity, storage cost, and replay determinism.
2 videos11 min
4
Conversational memory strategies and schemas
Go beyond raw chat history: structured conversation memory (facts, preferences, tasks), summarization policies, episodic vs semantic memories, and how memory writes are triggered and validated. Emphasize avoiding hallucinated memories and memory drift.
2 videos8 min
5
Context window management and packing
Manage limited context windows using sliding windows, hierarchical summaries, and relevance-based packing. Cover failure modes like lost-in-the-middle, prompt injection via retrieved text, and techniques for ordering/formatting evidence for maximum utility.
2 videos9 min
6
Vector database for agent memory
Design vector-store-backed memory: chunking strategies, embedding choices, metadata schemas, filters, and refresh/re-index policies. Emphasize retrieval quality, latency/cost, and multi-tenant access control for persistent agent memory.
2 videos12 min
7
RAG retrieval and grounding patterns
Engineer RAG beyond the basics: query rewriting, multi-step retrieval, reranking, citations/grounding, and controlling evidence volume to prevent degradation. Connect retrieval to context packing to avoid over-retrieval and lost-in-the-middle.
2 videos12 min
8
Long-term memory persistence and governance
Persist memory across sessions with durable stores (SQL/NoSQL/object storage) plus semantic indexes, using structured metadata for TTL, versioning, auditability, and access control. Cover privacy, consent, and strategies for updating/forgetting memories safely.
1 video4 min
Start Learning
Begin your learning journey
Modules8
Duration60 min
Science-backed learning
In-video quizzes and scaffolded content to maximize retention.
Key concepts
Agent Memory Layers And LifecyclesDeterministic State Updates With ReducersCheckpointing, Replay, And Safe Rollback