Hi everyone, Majid here (co-founder & CTO). An announcement for the Moorcheh community first, because you've been with us longest.
On Tuesday, June 16, we're launching Memanto on Product Hunt our open-source memory agent that gives Claude Code, Cursor, Codex, and a dozen other AI agents persistent memory across sessions. It's the first product built end-to-end on Moorcheh's retrieval engine, and many of you have already seen pieces of it in the repo and on our YouTube channel.
What makes this launch different from what we've shipped before:
The entire stack now runs locally, for free. One pip install, and Memanto sets up Moorcheh on-prem, embedding models, and a local LLM via Ollama on your own machine. No API key, no data leaving your laptop. The free cloud option is still there, and you can switch between the two.
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.
Give your AI agents long-term memory. Memanto lets agents carry context across sessions with instant semantic recall, built-in RAG, and cost-efficient serverless architecture or completely on-prem. No need for VDBs. Works with Claude Code, Cursor, Windsurf, and 10+ more tools.
