Hacker News: majidfekri

New comment by majidfekri in "Springer Nature has removed two studies by Max Planck"

majidfekri — Fri, 26 Jun 2026 16:51:27 +0000

Everything is an advertisement and nothing is just an advertisement.

New comment by majidfekri in "Springer Nature has removed two studies by Max Planck"

majidfekri — Fri, 26 Jun 2026 15:56:56 +0000

I wrote a whole chapter about Max Planck and his challenges and his legacy in my book "What is light? Wave theory of light and origins of ether in science" check it out if you are interested

I Wish I Knew This Before Building an AI Second Brain

majidfekri — Fri, 26 Jun 2026 13:27:47 +0000

Article URL: https://pub.towardsai.net/i-wish-i-knew-this-before-building-an-ai-second-brain-6179aa439aef

Comments URL: https://news.ycombinator.com/item?id=48686390

Points: 1

# Comments: 0

Information-Theoretic Vector Search Is Having Its Moment

majidfekri — Mon, 22 Jun 2026 14:21:47 +0000

Article URL: https://moorcheh.ai/blog/information-theoretic-vector-search-turboquant-moment

Comments URL: https://news.ycombinator.com/item?id=48630522

Points: 2

# Comments: 0

New comment by majidfekri in "Memanto; open-source memory agent that remembers, recalls and answers"

majidfekri — Thu, 18 Jun 2026 15:51:30 +0000

To answer your first question, I have to say no. agentic memory benchmarks do not reflect the nuances and difficulties that real agents encounter in real workflows. We hope there are better more practical benchmarks being developed. Second question I assume by LLM you mean AI agents; if that is the case, yes, the whole agentic work experience is different when you have an active memory agent to rely on.

New comment by majidfekri in "Memanto; open-source memory agent that remembers, recalls and answers"

majidfekri — Thu, 18 Jun 2026 14:51:20 +0000

I assure you it is not a vibe coded pg_vector wrapper. It is built on top of a custom made search engine that is state-of-the-art in semantic search. Check out moorcheh.ai, cloud infrastructure, moorcheh on-prem and moorcheh-on-edge. Here is the paper explaining how we came up with the idea of memanto: https://arxiv.org/abs/2604.22085

New comment by majidfekri in "Memanto; open-source memory agent that remembers, recalls and answers"

majidfekri — Thu, 18 Jun 2026 14:39:12 +0000

Thanks for your comment but Memanto is not a "memory layer" it is an active "memory agent". The difference is that memanto is not a passive layer it is an actual agent and it has its own intelligence and AI capabilities independent of your agents.

New comment by majidfekri in "Memanto; open-source memory agent that remembers, recalls and answers"

majidfekri — Thu, 18 Jun 2026 14:17:02 +0000

We have built our own infrastructure on moorcheh.ai, it was the first information-theoretic search engine before Google's research. Moorcheh whitepaper: https://arxiv.org/pdf/2601.11557

New comment by majidfekri in "Memanto; open-source memory agent that remembers, recalls and answers"

majidfekri — Thu, 18 Jun 2026 14:10:49 +0000

I am so glad you like it :) your comment made my day!

Memanto; open-source memory agent that remembers, recalls and answers

majidfekri — Thu, 18 Jun 2026 13:54:36 +0000

Article URL: https://github.com/moorcheh-ai/memanto

Comments URL: https://news.ycombinator.com/item?id=48585402

Points: 14

# Comments: 11