Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
WikiMem
The talk demonstrates how to implement persistent, wiki‑style memory for large language models using HTTP‑exposed MCP tools, enabling real‑time knowledge updates.
Memory for LLMs; viewable as a wiki
Related projects
Memory AI
Boston
The talk explains a memory‑AI system that stores user interactions securely via encryption, using vector search, AI chat…
Building A LLM Brain For My BorgIOS
Waterloo
This talk covers the Mnemosyne Protocol, a decentralized, tamper-proof memory system for AI agents enabling persistent, secure, and…
Making Memories with Well Crafted Prompts
Seattle
Learn how to let Claude shell into target systems, generate STAR‑style postmortems, and have agents review lessons learned…
Long term and short term memory
Los Angeles
A demo of a Gradio interface using ChromaDB to store and retrieve conversation embeddings, enabling long‑term memory with…
aius.co—the long-term memory agentic framework
Poland
The session explains aius.co’s modular agentic architecture, detailing long‑term memory persistence, compute allocation, and autonomous evolution of agents…
SQL-First AI Memory: Building Developer Tools with WebMCP and Browser-Native Databases
Seattle
Live demo of an AI agent using WebMCP to run SQL queries on an in‑browser PostgreSQL database, navigating…