A self-hosted Claude assistant on a Raspberry Pi, with compounding memory via a knowledge graph and synthesised wiki pages.
claude ai-assistants self-hosting
Notes
Writing on data engineering, AI in production, and things I've learned the hard way. 7 posts
All
#claude (1)
#ai-assistants (1)
#self-hosting (1)
#dbt (1)
#databricks (2)
#data-engineering (1)
#data-migration (2)
#snowflake (2)
#gdpr (1)
#lakehouse (1)
#data-platform (1)
#failure-modes (1)
#AI (1)
#GDPR (1)
#RAG (1)
#context-engineering (1)
#open-source (1)
#enterprise (1)
The three SQL syntax, schema reference, and state management problems I keep seeing when teams migrate from Databricks to dbt; and how to fix each one.
dbt databricks data-engineering
How I migrated 250 BI users from SQL Server 2012 to Snowflake, cutting reporting latency from daily to hourly and bringing the platform into GDPR compliance.
data-migration snowflake gdpr
How I migrated 20M+ records from Databricks to Snowflake, cutting monthly infrastructure costs by 40% and fixing years of accumulated governance debt.
data-migration snowflake databricks
Three patterns that derail lakehouses in production: the swamp lakehouse, the performance mirage, and the metadata ghost town.
lakehouse data-platform failure-modes
GDPR checklist for RAG systems: data inventory, vector storage, deletion pipelines, and audit trails; tested across three DACH audits.
AI GDPR RAG
RAG returns the closest document. ECL returns the reasoning your experts use, cited and conflict-aware. Open source, built on Andy Chen's pattern.
context-engineering open-source enterprise