Victor García

Architect

Madrid Joined on Mar 12, 2026 https://micelclaw.com

Victor García

Mar 27

PII-aware routing: how to use cloud AI and keep your sensitive data local

#privacy #ai #architecture #selfhosted

9 min read

Want to connect with Victor García?

Create an account to connect with Victor García. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Victor García

Mar 26

Sleep-time compute for personal data: what your AI should do while you sleep

#ai #architecture #postgres #selfhosted

10 min read

Victor García

Mar 24

Hybrid search with RRF: combining pgvector, tsvector, and a knowledge graph in one query"

#postgres #search #pgvector #ai

9 min read

Victor García

Mar 20

Your AI agent is wasting 90% of its tokens on field names"

#ai #architecture #llm #optimization

7 min read

Victor García

Mar 19

From JSON to compact: reducing API payloads 60% for LLM consumption"

#api #ai #typescript #architecture

7 min read

Victor García

Mar 18

Heat scoring: teaching your data to forget (gracefully)"

#postgres #architecture #ai #search

7 min read

Victor García

Mar 18

Building a personal knowledge graph with just PostgreSQL (no Neo4j needed)"

#postgres #database #knowledgegraph #architecture

9 min read

Victor García

Mar 14

Entity extraction with a 2B model: benchmarks from a personal knowledge graph"

#ai #nlp #ollama #selfhosted

8 min read

Victor García

Mar 14

The 4-slot hook pipeline: how every CRUD operation feeds four systems at once"

#architecture #postgres #typescript #ai

7 min read

Victor García

Mar 13

137 migrations and counting: building a personal OS schema from scratch

#postgres #database #architecture #selfhosted

6 min read

DEV Community

Victor García

Badges

1 Week Community Wellness Streak

Writing Debut

PII-aware routing: how to use cloud AI and keep your sensitive data local

Want to connect with Victor García?

Sleep-time compute for personal data: what your AI should do while you sleep

Hybrid search with RRF: combining pgvector, tsvector, and a knowledge graph in one query"

Your AI agent is wasting 90% of its tokens on field names"

From JSON to compact: reducing API payloads 60% for LLM consumption"

Heat scoring: teaching your data to forget (gracefully)"

Building a personal knowledge graph with just PostgreSQL (no Neo4j needed)"

Entity extraction with a 2B model: benchmarks from a personal knowledge graph"

The 4-slot hook pipeline: how every CRUD operation feeds four systems at once"

137 migrations and counting: building a personal OS schema from scratch