We made the entire stack run locally for free — would love your honest take on the experience
Hey everyone, Majid here, co-founder and CTO. 👋
Memanto is a memory agent for your AI agents — it remembers, recalls, and answers, so Claude Code, Cursor, Codex (and ~14 other agents) stop forgetting your project every time the context resets.
The big change we're launching today: the whole stack now runs 100% locally and free. pip install memanto, one command, and it sets up everything on your machine — retrieval engine, embedding models, even a local LLM via Ollama. No API key, no vector DB to manage, nothing leaves your laptop. If you prefer zero-install, there's a free cloud option too, and you can switch between them.
We also built one-command migration, so if you're on Mem0, Zep, or Letta, you can bring your existing memories over and compare side by side.
Two things I'd genuinely love feedback on from this community:
The first 5 minutes. We've obsessed over install friction — if anything in the local setup made you pause, even for a second, tell me here and I'll fix it or explain it.
What should memanto migrate support next? We picked Mem0/Zep/Letta first, but I'd rather build for what you're actually using.
Benchmarks, the research paper, and an interactive evaluator where you can inspect every retrieval are linked on the page for anyone who wants to go deep. I'll be in this thread all day — ask me anything, including the hard questions.
Replies