Memory
Memory is a storage resource or mechanism that retains data or computational state for access during computation or later use.
AI Agents in Action, Second Edition
Agent memory is information retained from prior interactions or external sources that can augment an agent's context.
- How it is used
- Supplies relevant past conversations, preferences, and agent experiences to the current context across tasks or sessions.
- How deep it goes
- Explains context limits, persistent storage, task state, and retrieval, then gives implementation and operational guidance without treating cognitive labels as mechanisms.
- Examples
- Contrasts message history with searched past conversations and shows session, retrieval, and preference-storage tools in a single-agent example.
- What you can do after
- Apply it via session history and selective long-term retrieval, with pruning, access filters, and grounded answers.
Read how AI Agents in Action, Second Edition explains memory →
Introduction to Generative AI, Second Edition
A memory system is a component that stores and retrieves information about users or prior interactions across conversations.
- How it is used
- Supports continuity across assistant conversations and preserves selected intermediate results during multistep agent tasks.
- How deep it goes
- Distinguishes task-level from cross-interaction memory and explains selection and recall at a high level, without implementation steps.
- Examples
- Uses weekly planning, retained search results, persistent assistant preferences, and a structured user-profile graph.
- What you can do after
- Evaluate/understand it by weighing useful continuity against inconsistent recall, corrupted memory, and the need for user control.
Read how Introduction to Generative AI, Second Edition explains memory →
Building Reliable AI Systems
A memory mechanism stores and retrieves information so an AI system can retain context across task steps or interactions.
- How it is used
- Maintains context across agent interactions and multistep workflows so users need not repeat earlier details.
- How deep it goes
- Distinguishes session from cross-session memory and implements buffer and summary patterns, but gives no persistent-storage recipe.
- Examples
- Uses a flight-booking follow-up, a LangChain message list, and a Python function that summarizes conversation turns.
- What you can do after
- Build it from scratch with a message list, or apply it via LangChain messages and an LLM-based running summary.
AI Agents and Applications
Memory is stored information that an agent or application can retain and use across steps or interactions.
- How it is used
- Maintains conversational context so chatbots and agents can answer follow-ups and continue stateful workflows.
- How deep it goes
- Works through chat-history integration and LangGraph checkpoints for short-term memory; defers implementation of system-specific long-term memory.
- Examples
- Tests references to the Romans in a history chatbot and to Penzance in a weather follow-up.
- What you can do after
- Apply it via LangChain chat history or LangGraph checkpoints to make an assistant retain short-term conversational context.
Fast Python: High performance techniques for large datasets
- How it is used
- Frames memory as a performance constraint for large-array processing and compact data storage.
- How deep it goes
- Introduces the hierarchy and measures an array-performance anomaly, but defers detailed explanation of cache behavior and matrix representation.
- Examples
- Benchmarks NumPy column and row expressions at two matrix sizes and compares hypothetical memory-hierarchy capacities and access times.
- What you can do after
- Evaluate/understand why similar array operations can have sharply different timings as data size grows.
Read how Fast Python: High performance techniques for large datasets explains memory →
Grokking AI Applications
Application memory is persisted conversational or task-related information that a software system can retrieve across interactions.
- How it is used
- Uses application-managed context to overcome the LLM’s statelessness across conversational turns.
- How deep it goes
- Explains statelessness, history capture, and prompt reinjection, then demonstrates a simple list-based implementation.
- Examples
- Demonstrates memory through Andrea’s name, disabled assistant memory, history snippets, and a Python chat loop.
- What you can do after
- Build it from scratch by storing conversation turns and injecting them into each subsequent model prompt.
Build an AI Agent (From Scratch)
Agent memory is a mechanism for retaining and retrieving information across an agent's reasoning steps or interactions.
- How it is used
- Keeps agent context manageable during a run and carries conversation or useful knowledge across later interactions.
- How deep it goes
- Details three implementation patterns, context-reduction methods, session components, and long-term storage and retrieval; limits conflict handling to ADD and SKIP.
- Examples
- Uses repeated run() calls with a session_id, stored problem-solving records, duplicate checks, and explicit or automatic memory retrieval.
- What you can do after
- Build it from scratch with session continuity, context optimization, and a vector-backed long-term memory pipeline.
Modern C
Main memory is the linearly addressable storage that holds a running program's instructions and data.
- How it is used
- Frames C storage behavior within a concrete machine model.
- How deep it goes
- Defines linear addressing and illustrates storage realization through assembler, but defers broader architectural detail.
- Examples
- Uses x86_64 assembler instructions that adjust the stack and load or store values at register-relative memory locations.
- What you can do after
- Evaluate how a simple C function's variables and operations correspond to registers and memory locations.
AI for Everyday IT
Physical memory is the hardware memory available to a computer system for storing active data and programs.
- How it is used
- Analyzes Oracle database configurations to find instances using more than 75% of available physical memory.
- How deep it goes
- Explains unit conversion and usage formulas, then applies them in a query while stopping short of broader hardware diagnostics.
- Examples
- Uses a configuration query, a row containing 15297 MB, and a CTE that normalizes M and G values.
- What you can do after
- Diagnose memory pressure by querying configurations, converting units, calculating usage, and filtering instances above a utilization threshold.
Fabulous Adventures in Data Structures and Algorithms
Memory is computer storage capacity available to hold program data during execution.
- How it is used
- Evaluates representation choices by comparing memory consumption with execution time and search performance.
- How deep it goes
- Calculates asymptotic and approximate byte costs, then stops short of a complete runtime memory model.
- Examples
- Compares Life-cell arrays, packed bits, ENABLE word lists, sorted C# lists, and trie nodes.
- What you can do after
- Evaluate memory–time trade-offs and estimate representation costs for arrays, strings, sorted lists, and tries.
Read how Fabulous Adventures in Data Structures and Algorithms explains memory →
Rust in Action: Systems programming concepts and techniques
RAM is volatile computer memory that stores data and instructions available to a running processor.
- How it is used
- Uses RAM to hold instructions and data for a CHIP-8 CPU, then connects memory to operating-system interaction and thread costs.
- How deep it goes
- Models RAM as a fixed byte array and demonstrates instruction reads and function loading, while broader OS memory behavior is introduced through examples.
- Examples
- Shows a 4 KB CHIP-8 memory array, function bytes loaded at 0x100, and memory demand from threads.
- What you can do after
- Build it from scratch by adding a memory array to a CHIP-8 CPU and loading function opcodes into RAM.
Read how Rust in Action: Systems programming concepts and techniques explains memory →
Build AI-Enhanced Web Apps
A software component or mechanism that retains information from prior interactions so an AI application can use ongoing context.
- How it is used
- Builds context-aware AI applications by retaining conversation history across ongoing interactions.
- How deep it goes
- Explains retrieval, session identifiers, message conversion, memory construction, and invocation, while leaving storage integration application-managed.
- Examples
- Uses session histories, stored messages, and a follow-up question that asks what the user previously asked.
- What you can do after
- Build it from scratch by retrieving messages, constructing ChatMessageHistory and memory, and invoking a ConversationChain.
Build Python Web Apps with Streamlit
Application memory is the transient information retained by a running application while it executes.
- How it is used
- Preserves conversation and application state across reruns or graph invocations so interactive applications can continue prior work.
- How deep it goes
- Explains state loss, in-memory checkpointing, and thread-based recall, while deferring durable database persistence to alternative checkpointers.
- Examples
- Uses a task list, a follow-up chatbot message, MemorySaver, and thread ID 1 as concrete examples.
- What you can do after
- Apply it via LangGraph by compiling a graph with MemorySaver and invoking it with a consistent thread ID.
Read how Build Python Web Apps with Streamlit explains memory →
ScyllaDB in Action
Memory is volatile storage available to a computing instance for holding active program and database state.
- How it is used
- Frames memory as one resource in ScyllaDB cluster planning alongside storage, CPU, networking, and cost.
- How deep it goes
- Identifies memory as a sizing concern but stops short of explaining capacity formulas, allocation, or workload-specific requirements.
- What you can do after
- Evaluate memory as part of a cluster baseline and validate the choice through production-level workload testing.
Related concepts
- working memoryincludes · Working memory is a limited, temporary store of information available for immediate access or manipulation during an active task or interaction.
- ReActpart of · ReAct is an agent technique that iteratively interleaves reasoning, actions, and observations so results can guide subsequent actions.
- statecontrasts with · State is information or a configuration describing the condition of a system, entity, or computation at a particular time and potentially influencing subsequent behavior or decisions.
- zero-page memoryincludes · Zero-page memory is the first 256 bytes of 6502 address space, whose locations can be specified with a one-byte address.
- large language modelcontrasts with · A large language model is a machine-learning model, typically neural, trained on extensive text data to process and generate language.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.