Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Postgres
Moving RAG From Pinecone to Postgres pgvector: Six Months Later
Moving RAG from Pinecone to Postgres pgvector, six months on: 9M vectors, real cost, latency and recall numbers, what got worse, and when pgvector is right.
7 min readHybrid Search in Postgres for a Health Assistant: Schema, Chunking, RRF and Evals
Hybrid search in Postgres for a health assistant: structure-aware chunking, pgvector with RRF, binary quantization, score thresholds and a proper evaluation.
19 min readDevice Leases in Postgres: Stop Parallel Agents Fighting Over Emulators
How a single Postgres table and a short bash script stop parallel Claude Code sessions from colliding on emulators and simulators, plus the three bugs the tests caught.
6 min readWe Dropped Our Vector Database: pgvector Served 40M Embeddings Fine
A migration story: replacing a paid vector store with pgvector on 40 million rows, including the backfill method, the recall mistake that hid in dashboards, and when not to switch.
5 min readLangGraph Persistence Part 2: PostgresSavers, HITL, and Production Backends
Move LangGraph from InMemorySaver to PostgresSaver with PostgreSQL pools and async savers, compare SQLite and Redis, and run interrupt and resume in prod.
10 min readCross-Thread Long-Term Memory Stores in LangGraph
Long-term memory across threads in LangGraph: store namespaces, put/get/search, semantic search over memories, deduped writes and Postgres-backed persistence.
19 min readSelf-Hosting LangGraph Agent Server With Postgres and Redis
Learn how Langhost swaps LangGraph's persistence layer for Postgres and Redis, letting teams self-host the unmodified Agent Server under an MIT license.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.