Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
vlite 2
Learn how a lightweight NumPy‑based vector database can replace traditional stores, serving as a fast context library and enabling personalized browser cookie management.
a simple and blazing fast vector database made in numpy
vlite: fast, NumPy-based vector database for RAG applications.
Related projects
moondream
New York City
Explore moondream, a 1.6B parameter vision language model that runs locally in real time, matching larger models' performance.…
Moondream - vision language model that runs locally in near real-time
Palo Alto
Learn how Moondream's compact vision-language model runs locally in near real-time, achieving performance comparable to larger VLMs on…
A smart file browser
Bengaluru
This talk covers a desktop file browser with smart folder triggers, AI file creation, and offline TTS/STT using…
Moondream 2
Seattle
This talk demonstrates the world’s smallest and fastest vision language model, exploring its capabilities and potential applications for…
V2C.dev - Video to Code
Boston
Learn how to turn a video into functional code, projects, and complete websites by extracting and translating visual…
LuminaLog - AI Journaling for self-development
Palo Alto
Explore how LuminaLog uses speech‑to‑text and an AI companion to analyze journal entries, offering concrete feedback, insights, and…