@memofsdev · X

@matebenyovszky · X

I use multiple providers Claude Code, Cursor, Codex, Hermes, Antigravity etc. and multiple machines. Over time, each one ended up with its own slightly different skills and tools 😰 So I started where a playbook is a portable bundle containing my MCP/OpenAPI servers, skills, prompts, personas and memory, which I can take with me into whichever environment I’m using. I’m still trying to figure out whether this is useful beyond my own workflow. Ideas? 🤔 🍎 Source / open source on Github: matebenyovszky/agentplaybooks I also built an npm CLI that audits a project and syncs the same skills and MCP definitions across harnesses.

mthines · HN

A couple of weeks ago I built an open source system for handling memory for agents, and it's called LoreKit. It supports local and remote (so you can share with colleagues for instance) memory, it's free, open source and REALLY easy to set up. Local memories requires no sign up, but remote does obviously - but sign up is just OAuth. It's retrieving memories lexically - so no embedding (for now), but using scopes and labels to make sure the memories you retrieve are relevant automatically. And it