A session transcript is authoritative about what was attempted. Git is authoritative about what shipped. For three months ENGRAM had only the first one, and I did not notice I was asking it the wrong questions.
Tag: technology
No Message Passed Between Them: ENGRAM Agents Coordinate Through Memory
The hard part of running a fleet was never spawning the agents or routing the tasks — your harness already does that. The hard part is what they know, and whether one agent’s finding can reach another without leaking to everyone. That is not a scheduling problem. It is a memory problem.
Where Memories Come From: ENGRAM Learns to Track Provenance and Group by Project
ENGRAM could already remember an enormous amount — articles, code sessions, conversations from half a dozen assistants. What it could … More
Completing the Mind: ENGRAM Now Remembers Conversations from Claude Desktop, ChatGPT, and Gemini
ENGRAM already remembered my articles and my code sessions. The last missing piece was the work I do with assistants … More
Claude Code and ENGRAM Knowledge Hub: recalling the good memories together
This is a follow-up post about the next layer of knowledge consolidation in ENGRAM Knowledge Hub. Ingestion of Claude Code sessions into the Knowledge Hub allowed me to close the gap between what I researched and planned and what I actually built, including the changes, feature design enhancements, and pivots that often happen during development.
ENGRAM Part 3: Hippocampal-Inspired Memory – Working Memory, Long-Term Memory, and Periodic Consolidation
How ENGRAM’s agents remember what matters across multi-turn research sessions, and how memory biases retrieval toward coherent results Introduction In … More
ENGRAM Part 2: Unified Graph Retrieval from Long Documents and Multi-Agent Response Synthesis
Part 2 of this blog explains how uploaded research papers join the knowledge graph through hierarchical extraction, and how specialized … More
ENGRAM Part 1: GraphRAG with Hippocampal-Like Associative Retrieval
Part 1 of this blog series explains how query-entity relevance spreading across a knowledge graph eliminates the need of typical … More
MCP, A2A, and Human-in-the-Loop: A Multi-Agent Threat Intelligence System in Practice
This blog describes a cybersecurity threat intelligence platform built in Python that models relationships between threat actors, attack techniques, vulnerabilities, … More
AI Agent with RAG-Assisted Declarative Query Generation for Data in Oracle Analytic Views
This blog is about a project I built to confirm an idea: LLM reasoning can generate declarative query specifications in … More
Igor's Musings About Technology 