Hacker News new | ask | show | jobs
Show HN: Memsprout – share your AI context with teammates (memsprout.com)
3 points by mat10112 11 days ago
I’m an architect at my company and everyone on my team is now using Claude/Codex agents for their work. Managing context in claude.md/agents.md files is fine but so much of the knowledge required doesn’t fit cleanly in one repo or the other. Plus, much of the team (product, design, support) does not work in repos but still needs a place to share context.

I searched for existing solutions to this but only found products meant for managing deployed AI agent memory for use in AI applications. I wanted something that would help my team share the context that lives in our collective heads.

First try at solving this problem was creating a directory structure with an MCP layer on top of it, but that became a pain to maintain. So I started tinkering with creating a platform for context sharing that works for the whole team. For this to work I wanted to prioritize two things above all else:

1. Easy to store valuable context. If it feels like maintaining docs, no one will use it. 2. Easy to share context with the right people. Access controls, read/write permissions, etc.

This turned into memsprout. Memsprout solves shared context with:

- MCP - to connect directly to AI agents right where everyone is doing their work already

- Memories - the core unit of thing that is stored

- Spaces - to manage sharing memories with teammates

- Topics - to categorize memories into specific buckets

So now I am able to store memories for bits of context I define as I work and share them with my teammates.

Q: Do you guys also see this kind of context sharing as a challenge? How have you solved it in your work?

1 comments

Also want to acknowledge this approach has some limitations. Human judgement in sharing and managing context is still crucial. What I think memsprout does is provide transparency in shared context management. But the last mile is still (and should still imo) be human owned.

And I thought of a concrete example as a use case: acronyms, code names, etc. Every company I have been at has tons of these. In my first attempt of a repo based approach we used an .md file as a “glossary” of company terminology. But updating that file became a tedious, focus shifting, task. With memsprout as soon as I explain to claude that “StepLadder” is our new product line, claude can store that as a memory and immediately make that new insight available to the rest of my team’s agents.