Methodology & Bibliography

How this glossary is sourced, what counts as a primary source, how freshness is managed, and the full 51-entry bibliography.

Data last refreshed: 2026-05-08. Next scheduled refresh: Q3 2026, or sooner on a vendor / regulator / paper trigger (see refresh cadence).

Sourcing rule

Every term in this glossary has a single canonical primary-source citation: a vendor or framework documentation page, a peer-reviewed or arXiv paper, an analyst publication where the analyst is the originator of the framing, or a standards-body specification. Wikipedia and secondary blogs are never a primary citation; if a concept only appears in such surfaces, the term does not yet warrant inclusion.

When more than one canonical source could be cited (e.g., RAG has the Lewis et al. paper and several vendor docs), the citation is chosen by hierarchy: peer-reviewed paper > standards body > vendor primary documentation > analyst publication.

Freshness flags

• Foundational — original peer-reviewed papers that anchor the field (Lewis et al. RAG 2020; Park et al. Generative Agents 2023; Liu et al. Lost in the Middle 2023; Malkov & Yashunin HNSW 2018; Robertson & Zaragoza BM25 2009; Cormack et al. RRF 2009; Jégou et al. Product Quantization 2011; Izacard & Grave Fusion-in-Decoder 2020; Wang et al. Voyager 2023; Shinn et al. Reflexion 2023; Packer et al. MemGPT 2023; Hogan et al. Knowledge Graphs 2021). Refreshed only if substantively revised.
• In force — binding standards or vendor specifications currently in effect (e.g., the W3C SPARQL 1.1 query language; Anthropic prompt-caching documentation as a billed product feature).
• Emerging 2026 — terms that entered mainstream discourse in 2025–2026 and are still stabilising (Mem0, A-Mem, GraphRAG, Agentic RAG, Context engineering, Context graph). Carried with explicit emerging flags so readers know the framing may evolve.
• Contested — terms with named, meaningful disagreement in the field; we carry both positions when they exist.

Refresh cadence

Quarterly term audit (next scheduled: Q3 2026). Trigger-based refresh on any of:

• A canonical-vendor SDK or doc page changes a term's framing (e.g., Anthropic's prompt-caching API, Cohere's rerank model, Pinecone's reranking guide).
• A new arXiv paper introduces a term that has crossed the bar from emerging to load-bearing.
• A vector-store vendor releases a new index family or quantisation technique that displaces a current default.
• The W3C, Neo4j, or another standards body updates a query-language specification cited here.
• A canonical-source URL 404s (citation rot is the fastest-acting decay).

Daily 15-minute news skim flows back into raw/research-notes.md under Open questions / follow-up. Findings accumulate between sprints; the next quarterly refresh sweeps them in.

Coverage scope

This glossary is intentionally scoped to memory architecture for LLM agents. It deliberately excludes general-purpose ML vocabulary (gradient descent, backpropagation, transformer architecture details) that does not bear on agent-memory design decisions. For broader agentic-AI vocabulary see the Agentic Glossary — Quick Reference; for narrative depth on flagship terms (RAG, Memory, Knowledge, Context graph) see the deep Agentic Glossary.

Bibliography (51 unique sources)

1. AgentsBooks — Anatomy of a Firm. https://agentsbooks.com/anatomy — accessed 2026-05-08
2. Anthropic — Building Effective Agents. https://www.anthropic.com/research/building-effective-agents — accessed 2026-05-08
3. Anthropic — Claude long-context model card. https://docs.claude.com/en/docs/build-with-claude/context-windows — accessed 2026-05-08
4. Anthropic — Effective context engineering for AI agents. https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents — accessed 2026-05-08 Emerging 2026
5. Anthropic — Long context prompting tips. https://www.anthropic.com/news/prompting-long-context — accessed 2026-05-08
6. Anthropic — Prompt caching. https://docs.claude.com/en/docs/build-with-claude/prompt-caching — accessed 2026-05-08 In force
7. Asai et al. — Self-RAG (2023). https://arxiv.org/abs/2310.11511 — accessed 2026-05-08
8. Cohere — Rerank model documentation. https://docs.cohere.com/docs/rerank-overview — accessed 2026-05-08
9. Cormack et al. — RRF (2009). https://plg.uwaterloo.ca/~gvcormac/cormacksigir09-rrf.pdf — accessed 2026-05-08 Foundational
10. Faiss — Approximate nearest neighbour wiki. https://github.com/facebookresearch/faiss/wiki — accessed 2026-05-08
11. Faiss — IVF documentation. https://github.com/facebookresearch/faiss/wiki/Faiss-indexes — accessed 2026-05-08
12. Gao et al. — HyDE (2022). https://arxiv.org/abs/2212.10496 — accessed 2026-05-08
13. Gartner — Hype Cycle for Agentic AI. https://www.gartner.com/en/articles/hype-cycle-for-agentic-ai — accessed 2026-05-08 Emerging 2026
14. Hogan et al. — Knowledge Graphs (2021). https://arxiv.org/abs/2003.02320 — accessed 2026-05-08 Foundational
15. Izacard & Grave — Fusion-in-Decoder (2020). https://arxiv.org/abs/2007.01282 — accessed 2026-05-08 Foundational
16. Jégou et al. — Product Quantization (2011). https://lear.inrialpes.fr/pubs/2011/JDS11/jegou_searching_with_quantization.pdf — accessed 2026-05-08 Foundational
17. Karpukhin et al. — Dense Passage Retrieval (2020). https://arxiv.org/abs/2004.04906 — accessed 2026-05-08
18. LangChain — ConversationSummaryMemory. https://python.langchain.com/docs/versions/migrating_memory/conversation_summary_memory/ — accessed 2026-05-08
19. LangChain — Memory in Agents. https://python.langchain.com/docs/how_to/migrate_agent/ — accessed 2026-05-08
20. LangChain — Query analysis (decomposition). https://python.langchain.com/docs/how_to/query_multiple_queries/ — accessed 2026-05-08
21. LangChain — Semantic chunker. https://python.langchain.com/docs/how_to/semantic-chunker/ — accessed 2026-05-08
22. Letta — Documentation. https://docs.letta.com/ — accessed 2026-05-08
23. Lewis et al. — Retrieval-Augmented Generation (2020). https://arxiv.org/abs/2005.11401 — accessed 2026-05-08 Foundational
24. Liu et al. — Lost in the Middle (2023). https://arxiv.org/abs/2307.03172 — accessed 2026-05-08 Foundational
25. Malkov & Yashunin — HNSW (2018). https://arxiv.org/abs/1603.09320 — accessed 2026-05-08 Foundational
26. Mem0 — Memory architecture for AI agents. https://docs.mem0.ai/overview — accessed 2026-05-08
27. Microsoft Research — GraphRAG. https://microsoft.github.io/graphrag/ — accessed 2026-05-08 Emerging 2026
28. Milvus — Documentation. https://milvus.io/docs — accessed 2026-05-08
29. Neo4j — Cypher Manual. https://neo4j.com/docs/cypher-manual/current/ — accessed 2026-05-08
30. Neo4j — Property graph model. https://neo4j.com/docs/getting-started/appendix/graphdb-concepts/ — accessed 2026-05-08
31. OpenAI — Embeddings guide. https://platform.openai.com/docs/guides/embeddings — accessed 2026-05-08
32. Packer et al. — MemGPT (2023). https://arxiv.org/abs/2310.08560 — accessed 2026-05-08 Foundational
33. Park et al. — Generative Agents (2023). https://arxiv.org/abs/2304.03442 — accessed 2026-05-08 Foundational
34. pgvector — GitHub. https://github.com/pgvector/pgvector — accessed 2026-05-08
35. Pinecone — Chunking strategies. https://www.pinecone.io/learn/chunking-strategies/ — accessed 2026-05-08
36. Pinecone — Documentation. https://docs.pinecone.io/ — accessed 2026-05-08
37. Pinecone — Reranking guide. https://docs.pinecone.io/guides/search/rerank-results — accessed 2026-05-08
38. Pinecone — Similarity search. https://docs.pinecone.io/guides/search/semantic-search — accessed 2026-05-08
39. Pinecone — Vector similarity explained. https://www.pinecone.io/learn/vector-similarity/ — accessed 2026-05-08
40. Pinecone — What is a vector database?. https://www.pinecone.io/learn/vector-database/ — accessed 2026-05-08
41. Qdrant — Documentation. https://qdrant.tech/documentation/ — accessed 2026-05-08
42. Robertson & Zaragoza — BM25 (2009). https://www.staff.city.ac.uk/~sbrp622/papers/foundations_bm25_review.pdf — accessed 2026-05-08 Foundational
43. Shinn et al. — Reflexion (2023). https://arxiv.org/abs/2303.11366 — accessed 2026-05-08 Foundational
44. W3C — RDF 1.1 Primer. https://www.w3.org/TR/rdf11-primer/ — accessed 2026-05-08
45. W3C — RDF Concepts. https://www.w3.org/TR/rdf11-concepts/ — accessed 2026-05-08
46. W3C — SPARQL 1.1 Query Language. https://www.w3.org/TR/sparql11-query/ — accessed 2026-05-08 In force
47. Wang et al. — Voyager (2023). https://arxiv.org/abs/2305.16291 — accessed 2026-05-08
48. Weaviate — Documentation. https://weaviate.io/developers/weaviate — accessed 2026-05-08
49. Weaviate — Hybrid search documentation. https://weaviate.io/developers/weaviate/search/hybrid — accessed 2026-05-08
50. Xu et al. — A-Mem (2025). https://arxiv.org/abs/2502.12110 — accessed 2026-05-08 Emerging 2026
51. Zhong et al. — MemoryBank (2023). https://arxiv.org/abs/2305.10250 — accessed 2026-05-08

Privacy and editorial discipline

This site reuses the AgentsBooks portfolio's controlled vocabulary — agent fleet, agentic firm, 8 primitives, complete-not-compete, auditable substrate — and never references private client identifiers. Voice is operator-grade, plural first-person, citation-anchored. Comparison-style claims about vendors quote the vendor's own published documentation; we do not editorialise inside a definition.

Updated 2026-05-08.