---
name: Amir Gorbani
role: Designer & Product Engineer · Human-AI Interaction
location: Amsterdam, NL
email: amir@unbody.io
links:
  website: https://amir.cloud
  github: https://github.com/amirhouieh
  linkedin: https://www.linkedin.com/in/amirhouieh
  twitter: https://x.com/amirhouieh
  mastodon: https://mastodon.social/@imamir
skills:
  - Human-AI interaction
  - Applied AI
  - Memory & context engineering
  - Agent systems
  - Interaction design
  - Generative UI
  - Personalization
  - Local-first software
  - Open source
  - RAG & retrieval
---

Amir is a design/product engineer working at the intersection of AI and human-computer interaction. Since 2016 his work has been about building software that adapts to people instead of asking them to adapt to it — across gesture recognition systems, semantic search engines, AI developer infrastructure, adaptive memory layers, and now interfaces for AI agents.

He is the founder of Unbody Lab, where he builds experimental AI software. Current projects: Unbody (open-source AI infrastructure — retrieval, memory, and generative features over any data source, used by thousands of developers), Adapt (open-source adaptive memory library — neurons that synthesise and evolve rather than store and retrieve), Agent Mind (persistent shared memory for AI coding agents built on the Adapt runtime), and Serene (local-first AI tool for therapists built on Adapt).

His work covers: AI memory systems, generative UI, human-computer interaction (HCI), human-agent-computer interaction (HAC), local-first software, and open-source AI infrastructure. He builds the infrastructure layer when it doesn't exist, ships the product, then finds the next layer. Local-first and open source are values, not features — software is only really yours when you run it, not rent it.
