How I replaced a JSON file with SQLite for my MCP server's failure library, enabling cross-machine sharing and concurrent writes without race conditions.
Hook
The JSON failure library worked great — until my agents started running on multiple machines. Suddenly, crash fixes logged on one server were invisible to agents on another. Worse, concurrent writes from parallel agents corrupted the JSON file.
I needed a real database. Here's how I upgraded to SQLite without rewriting the whole library.
The Fix
SQLite is the perfect upgrade path. It's a single file, supports concurrent readers, and handles writes with proper locking. Here's the migration:
How I built a failure library into my MCP server so AI agents can cache solutions and warn each other about crashes before they…
AI agents reframe the state-placement problem: high-churn work state wants to live close to the actor, while ledgers and…
Last Tuesday I was deep in a session with an AI assistant, rewriting a caching layer that had been...
Giving an LLM a database connection is one of those ideas that sounds great in a demo and terrifying...
TL;DR My autonomous coding agent once opened the same pull request three times because it...
Meet Passport 🧳 — a shared memory layer for your AI coding agents. I have three AI coding agents...
