Viewing profile — itstomo

How does your team manage your team documentation? At work we use Google Docs and its MCP, and most of my colleagues use Codex to write any documents. For my side projects, we use …

I've developed a framework for multimodal semantic search (RAG), which orchestrates MongoDB, Pinecone, S3 bucket, LLM API, etc. If you are not too familiar with "semantic search," …

Looks like the hardware needed to run state-of-the-art open source LLM will be ~100kg... haha It's not feasible today. Someday!

Hey HN, If there is a pocket-sized compact hardware that hosts large-size open-source LLMs that you can connect offline, wouldn't it be helpful? The benefits: - You can use large-s…

Hey hacker news, I'm looking for an AI agent that completes arbitrary tasks by using the entire PC (screen view + clicking buttons etc). I know there are many attempts to achieve t…

I'm developing a truly multimodal database by document db, object storage, and vector db into a nicely unified interface. Traditionally, text and other media files such as images, …

What fantasy? I mean only things that are possible are possible. There is no fanstasy.

chat AI (2023) -> -> AI agent (2204) -> MCP (early 2025) -> ??? (2025~) So... for an AI agent to be truly self-evolving, it has to have access to modify ITSELF, not only the outsid…

There is no truly multimodal semantic search database. So I wanted to make one. https://www.capydb.com

Product Hunt is staged and stolen. You can visit PH at 12am (PST) and see 10 products that get 50 upvotes immediately after launching. If you don't buy upvotes, you'll be wiped out…

2023 was a year of pure upgrade of LLM models. 2024 was a year of improvements with more complex reasonings. 2025 might be the year of self-evolving AI agents with the capabilities…

The current LangChian approach is framework-oriented, which treats frameworks themselves as the central part of the system and databases as a sub-part of the system. This gives a h…