AI Agents Memory Empowered by Knowledge Graphs
For anyone designing their first agent memory system.
Understand where retrieval ends and memory begins, and how a knowledge graph helps an agent reason.
Read on Leanpub →The catalogue
18 published. Four shelves: how an agent remembers, how to model what it knows, the databases it remembers on, and how architecture turns into business impact. Not all of it needs a cover-to-cover read — the guide below says which books do. Everything is on Leanpub, where the pricing is yours to set.
Choose your first book
Graph Engineering: The Loop That Remembers
For engineers maintaining a graph that changes over time.
Explore the loop of extraction, consolidation and forgetting that keeps agent memory useful.
Read on Leanpub →Clarity Engineer: Code Is the Side Effect
For architects and engineering leads accountable for outcomes, not output.
See how clear decisions — not more code — are what move the business.
Read on Leanpub →What to read in depth, what to read quickly
Read in depth
The arguments the rest of the work stands on. Read cover to cover, and expect to come back.
- AI Agents Memory Empowered by Knowledge Graphs The foundation — the vocabulary every other book assumes.
- Beyond Context Graphs Memory as process, not storage — the shift that changes the architecture.
- Temporal Aware AI Memory Most production memory bugs are time bugs. This is where they are solved.
- Graph Engineering: The Loop That Remembers For teams running memory in production, not just designing it.
- Fact-Based Agents The modelling discipline that lets domain experts and agents share one model.
- Metagraph for AI Agents Provenance, context and statements about statements — read before you pick a schema.
- Edge AI: Pocket Knowledge Graphs on User Device The architecture case for on-device memory — privacy, cost and latency together.
- Clarity Engineer: Code Is the Side Effect For architects and leads: how clear decisions, not more code, create business impact.
Read quickly
Skim for the idea, then keep at hand as a reference for when the problem is in front of you.
- World Models for AI Agents A framing to borrow: read for the model of the environment, skip the detail until you need it.
- Semantic Space Time for AI Agent Ready Graphs Four relation types worth knowing; the idea lands in a chapter.
- Dependent Types & Logic for AI Agent Ready Knowledge Graphs Formal foundations — skim for the ideas, go deep only if you design the schema layer.
- LadybugDB for Edge Agent AI Memory A handbook: read the first chapters, return when you build on it.
- TypeDB for Edge AI Agents A handbook: the modelling chapters travel to any typed store.
- GraphDuck: DuckDB for Embedded AI Agents and Graphs A handbook: useful when DuckDB is already in your stack.
- Cypher 103 with LadybugDB A pattern catalogue — keep it open next to the editor.
- Rusty Graphs — AI Ready Graphs for Rust Developers A survey of the Rust ecosystem — for Rust teams.
- Clarity Forge: Local Coding Agent Done Right Practical setup for a hybrid human-and-agent workflow; read the parts you will use.
- Philosophical Wednesdays with an AI Powered Architect Short essays — one at a time, in any order.
The catalogue, as a graph
Every book is a node; every subject is a hub. Choose a subject to keep only the books that carry it — or choose a book to read what it is about.
Agent memory
Start here. What memory means for an agent, how it changes over time, and the engineering loop that keeps it honest.
-
AI Agents Memory Empowered by Knowledge Graphs
Read in depthThe starting point: why retrieval alone is not memory, and how a knowledge graph gives an agent something it can reason over instead of merely search.
Read on Leanpub → -
Beyond Context Graphs
Read in depthAgentic memory as a set of cognitive processes rather than a store — extraction, consolidation, and promise graphs for agents that cooperate without a central authority.
Read on Leanpub → -
Temporal Aware AI Memory
Read in depthTime as a first-class dimension in agent memory: bi-temporal facts, decay, recency-aware retrieval, and causal ordering across episodic and semantic stores.
Read on Leanpub → -
Graph Engineering: The Loop That Remembers
Read in depthThe engineering loop around a graph that keeps learning: what to extract, what to consolidate, what to forget, and how to keep the whole thing honest over time.
Read on Leanpub → -
World Models for AI Agents
Read quicklyA structured representation of the environment an agent reasons about, and how to build one that supports decisions rather than descriptions.
Read on Leanpub →
Knowledge modelling
How to shape what an agent knows so it can reason over it, not just retrieve it.
-
Fact-Based Agents
Read in depthElementary facts as the unit of agent knowledge. Attribute-free modelling that a domain expert can read back as sentences — and an agent can reason over without guessing.
Read on Leanpub → -
Metagraph for AI Agents
Read in depthHigher-order structure — edges over edges, hyperedges, reified relations — for agents that must reason about statements, not just facts. Bipartite encodings aligned with HyperGraphRAG.
Read on Leanpub → -
Semantic Space Time for AI Agent Ready Graphs
Read quicklyMark Burgess's Semantic Spacetime ontology — NEAR, LEADS-TO, CONTAINS, EXPRESSES — applied to build graphs whose semantics stay consistent under retrieval and reasoning.
Read on Leanpub → -
Dependent Types & Logic for AI Agent Ready Knowledge Graphs
Read quicklyWhat dependent type theory and higher-order logic offer a knowledge graph: constraints that hold by construction, and models that cannot express nonsense.
Read on Leanpub →
Embedded & edge substrates
Hands-on handbooks for the databases memory runs on. Read the one for your stack; skim the rest.
-
Edge AI: Pocket Knowledge Graphs on User Device
Read in depthA knowledge graph that fits in a pocket. Local-first, privacy-first memory that ships as a file and runs in-process — no server, no network hop, nothing leaving the device.
Read on Leanpub → -
LadybugDB for Edge Agent AI Memory
Read quicklyAn embedded columnar graph database as the substrate for agent memory: how it stores, how it traverses, and why in-process changes what an agent can afford to ask.
Read on Leanpub → -
TypeDB for Edge AI Agents
Read quicklyStrongly-typed knowledge graphs as on-device agent memory: PERA modelling, polymorphic entity-relation-attributes, and SHACL-style validation at the edge.
Read on Leanpub → -
GraphDuck: DuckDB for Embedded AI Agents and Graphs
Read quicklyGraph workloads on a columnar analytical engine. What DuckDB gives you for free, where it needs help, and how far an embedded analytical store carries agent memory.
Read on Leanpub → -
Cypher 103 with LadybugDB
Read quicklyCypher past the tutorials — the query patterns that actually come up when a graph is doing an agent’s remembering for it.
Read on Leanpub → -
Rusty Graphs — AI Ready Graphs for Rust Developers
Read quicklyBuilding agent-ready graph infrastructure in Rust: the crates, the trade-offs, and the parts you still have to write yourself.
Read on Leanpub →
Architecture & practice
How engineering decisions turn into business outcomes: clarity, judgement, and working alongside agents.
-
Clarity Engineer: Code Is the Side Effect
Read in depthThe argument that an engineer’s real output is clarity, and the code is what falls out of it. What changes when you take that seriously.
Read on Leanpub → -
Clarity Forge: Local Coding Agent Done Right
Read quicklyBuilding a coding agent that runs on your machine and earns its place in the loop — context, memory, and the discipline that keeps it useful past the demo.
Read on Leanpub → -
Philosophical Wednesdays with an AI Powered Architect
Read quicklyWeekly arguments with a machine about architecture, meaning, and what we are actually doing. Less a manual than a record of thinking out loud.
Read on Leanpub →
Prices on Leanpub are variable — you choose what to pay above the minimum, and the book keeps updating after you buy it.