Artem Baygot's profile on Product Hunt

About

Founder working on AI products and infrastructure. Interested in scalable systems, practical use cases, and turning ideas into real tools.

Links

AgentID

Badges

Tastemaker

Gone streaking 10

Gone streaking

Gone streaking 25

View all badges

Maker History

AgentIDOne identity. Shared memory. Every agent. Every tool.
Apr 2026
PersonaWarsCreate custom AI personas - watch 🤖 and 🙎🏻‍♂️ judge them
Mar 2026
FriendNDAA simple way to ask friends to keep things private
Feb 2026
Gym Traffic LiveAI-powered gym traffic & equipment usage tracker
Mar 2025

🎉

Joined Product HuntMarch 27th, 2025

Forums

p/agentid-2

•

6d ago

Why are AI agents still stateless in 2026?

Every time I switch tools or start a new session, my agents forget everything.

Same prompts. Same setup. Same explanations.

Feels like we are rebuilding the same agent over and over again.

So I started building AgentID to fix this
A persistent identity with shared memory across agents and tools

•

4d ago

AgentID - One identity. Shared memory. Every agent. Every tool.

AgentID gives every AI agent a persistent identity, shared memory, and full visibility. Works with every agent you already use - Claude, Cursor, Codex, OpenClaw, Nanobot and you name it :) No lock-in. No rewrites. One identity across all tools. Your agents share what they know, coordinate on tasks, and you see every action live - every token, every step, one screen.

•

5d ago

Featured

Are we over-engineering AI memory? (Markdown vs. Vector DBs for small datasets)

Hey makers!

Lately, I ve been looking closely at how independent builders and small teams are managing AI knowledge bases. It feels like the default "industry standard" is to immediately reach for a complex RAG pipeline and a heavy, paid Vector Database.

But I'm starting to wonder if we are over-engineering this for 90% of standard use cases.

Vector DBs are incredibly powerful for massive scale, but for smaller or non-massive datasets, they can be expensive, complex to query, and act as complete black boxes. If a search returns a weird chunk, diagnosing it is often a nightmare.