Show HN: MemorySync – Memory for AI Agents
I created MemorySync because I kept running into the problem of AI agents not being able to remember useful things about users between conversations. I wanted an easy way to give the agents memory in my application without having to build the whole thing myself. MemorySync is an API for giving AI agents memory. The application sends MemorySync information provided by the user, MemorySync saves useful memories for that user, and they can be retrieved later when needed. Give it a try without creating an account: https://memorysync.io/try Store a memory, refresh the page, and ask for it back to see if it remembers. If you're interested in using the API, I put the documentation here: https://docs.memorysync.io/ It's hosted only at the moment, so there is no self-hosting option. It's currently available in one US region, and it takes a few seconds to store a memory. The free plan allows 10k saves and 1k searches per month, and no credit card is required. I'd like to know if you think this is a useful abstraction for building AI agents, and what else you would expect from a memory API.
Discussion Highlights (1 comments)
mohd_rafay
Hey HN, creator here! I made MemorySync since I was getting bored of having to setup dedicated vector databases, embedding pipelines, and session storages every single time I wanted to make a LLM agent persistent. How it works: you make a call to an endpoint to store a bit of context about a particular user, and then make calls to an endpoint to fetch his memories in a conversation that takes place later. Everything is taken care of behind the scenes, so you don't have to worry about the infrastructure. Limitations currently: it's deployed in one US region and isn't self-hostable, although I wouldn't mind if someone asked for it. What do you think of the API interface? What must-have functionality should be included in an agent's state management?