[ memanto / blog ]

Field notes from a memory layer in production.

Engineering deep dives and tutorials on building, scaling, and shipping AI agents that remember. Written by the team behind Memanto.

4posts3deep dives1tutorials~9avg min read
ALL POSTS · NEWEST FIRST4 results
What Memanto Actually Stores: All 13 Memory Types Explained
EngineeringMay 4· 9 min read

What Memanto Actually Stores: All 13 Memory Types Explained

Not all context is the same. Memanto organizes every memory into one of 13 semantic types — each captured, retrieved, and surfaced differently. Here is what each type stores, why it exists, and when to use it.

Hetkumar PatelSoftware Developer
PREVIEWMEMORY · 9-min deep dive · published May 4
One Memory Layer, Every Tool: Connect Memanto Across Your Entire Dev Stack
TutorialsMay 4· 10 min read

One Memory Layer, Every Tool: Connect Memanto Across Your Entire Dev Stack

Your AI coding assistants forget everything between sessions. Here's how to wire Memanto into Claude Code, Cursor, Windsurf, and Cline simultaneously — so every tool knows your preferences, past decisions, and recurring errors.

Hetkumar PatelSoftware Developer
PREVIEWTUTORIAL · 10-min deep dive · published May 4
Why We Don't Use HNSW For Agent Memory Search
EngineeringApr 22· 8 min read

Why We Don't Use HNSW For Agent Memory Search

Standard vector databases lean on knowledge graphs and parallel pipelines to compensate for HNSW's approximate search. Information-Theoretic Scoring removes the need for both — and matches hybrid systems on every public benchmark.

Rasa RahnemaSoftware Developer
PREVIEWARCHITECTURE · 8-min deep dive · published Apr 22
Stop Overengineering Agentic Memory: How Basic RAG Outperforms the Leading Memory Frameworks
EngineeringMar 26· 8 min read

Stop Overengineering Agentic Memory: How Basic RAG Outperforms the Leading Memory Frameworks

Why complex graph-based memory architectures may be overkill, and how a highly-optimized RAG pipeline hits 89.8% on LongMemEval and 87.1% on LoCoMo with vector-only retrieval — no graph database, no multi-query orchestration.

Rasa RahnemaSoftware Developer
PREVIEWBENCHMARK · 8-min deep dive · published Mar 26