Hemory
2 commentsThe first launch from Hemory
Hemory is an always-on listening agent that captures spoken conversations and turns them into searchable, structured memory that AI agents can query through MCP. It runs quietly in the background, transcribing what it hears and organizing it into a knowledge base indexed by topic, person, and time. The memory layer sits between your daily conversations and the tools you work in, so an agent answering a question can reference something you said three weeks ago without you having to write it down.
Meet the team
What people who use it say
Nobody has reviewed Hemory yet. If you have used it, you are the one who can say whether it holds up.
Write the first review
Sign in to comment
The number of times I have thought 'someone mentioned that tool in a call last month' and had no way to find it is embarrassing. Hemory records what you say out loud and makes it searchable the way your text already is.
The MCP integration is what convinced me this is more than a transcription tool. An agent that can answer 'what did we decide about the API structure' by reading your actual conversations is solving a real information loss problem. I have not run it long enough to know whether always-on listening is something I will keep enabled. The privacy surface is obvious and worth thinking through before you turn it on.
Okay, the "what did we decide about X" use case is painfully real for me. Half my client calls end with a decision nobody wrote down, and two weeks later everyone remembers it differently. How do you handle the other people on the call? That's the part I'd need to sort out before turning it on with clients.