There are dozens of AI memory tools now. Here's why I relaunched mine anyway.

If you build with AI agents, you've seen it: memory tools are everywhere. Mem0, Zep, Letta, Supermemory, Basic Memory, Cognee, plus the memory built into Claude and ChatGPT. Most of them are good.

My problem started in 2025. My team and I ran several coding agents on the same projects, and every session started from zero. The memory tools available were mostly paid, cloud-hosted services, which meant sending our working context to someone else's servers. I wanted memory on my own machine that every agent could share and that I could inspect.

So about six months ago we built SuperLocalMemory and released it as open source. It now gets thousands of installs a month, and running it taught us something we didn't expect: the dangerous failure isn't forgetting. It's an agent finding a note that's related to the question, treating it as the answer, and building the next ten steps on it.

Most memory systems return the closest match they have. So we rebuilt SuperLocalMemory around one rule: memory has to be allowed to say no.

What changed:

- Recall returns supported, related, or "That isn't in SuperLocalMemory."

- An answer check asks whether the memories found actually answer the question: Laya on your Mac, or Jev online with your consent.

- One memory shared by Claude Code, Codex, Cursor and any MCP agent, and your agents can message each other.

- Pictures and PDFs you find by describing them, with Google's EmbeddingGemma 2 running locally.

- Roles, an audit trail, and erasure that reaches every copy.

It runs on your machine, it's open source, and four arXiv papers sit behind it. We're relaunching it here on Thursday, 15 October. (https://www.producthunt.com/products/superlocalmemory-v2?launch=superlocalmemory)

A question for you: with so many memory tools around, what would make you trust one enough to let your agent act on what it remembers? And if you run more than one agent, where has shared memory helped you, and where has it bitten you?