Tokenless

OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack

Dr. Lech Kalinowski presents Vault, a unique AI-native handheld terminal built on an ESP32-S3, featuring a dual-display (OLED for live interaction, e-paper for static content) and powered by a single battery. It operates in four modes—shell, assist, control, and an LLM-native RPG—and controls autonomous OpenClaw agents against a local, self-hosted 120B parameter GPT model served by NVIDIA TensorRT-LLM. The talk delves into the AI-native architecture, why inference remains on the backend, real-time agent thinking surfacing on e-paper, engineering challenges, and LLM-native game design, highlighting the potential for calm, text-first AI interaction.

2 min read
OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack
source: https://www.youtube.com/watch?v=akk6KRlcwW4

Dr. Lech Kalinowski introduces Vault, an AI-native, text-first, dual-display handheld terminal, born from a desire to build a physical device that feels like it’s from the future. His initial motivation was to create a remote controller for his OpenClaw instance on a DGX Park, recognizing that initial interactions with LLMs are primarily text-based.

Vault Device Design and Functionality

Vault is built around a single ESP32-S3 microcontroller and powered by one battery cell. Its core innovation lies in its dual-display approach: a fast, emissive OLED for dynamic

Share post

Stay In The Loop! Subscribe to Our Newsletter.

Get updates straight to your inbox. No spam, just useful content.

Recommended for You

Building an Agentic Platform — Ben Kus, CTO Box

Building an Agentic Platform — Ben Kus, CTO Box

Ben Kus, CTO of Box, outlines the technical evolution of their AI platform, detailing the transition from a promising but fragile LLM-based metadata extraction system to a robust, scalable agentic architecture. He explains why this shift was necessary to handle enterprise-level complexity and the key lessons learned.

Memory and Continual Learning: Engram's Dan Biderman and Jessy Lin

Memory and Continual Learning: Engram's Dan Biderman and Jessy Lin

Dan Biderman and Jessy Lin of Engram introduce their "always training" paradigm, focusing on baking a team's knowledge directly into a model's weights to achieve true memory and continual learning. This contrarian approach, which they call a "RAG killer" for specific use cases, promises up to 100x token savings and superior performance by internalizing context rather than relying on ever-larger context windows or external retrieval, envisioning a future where everyone has their own continually learning, personalized AI model.