AI Meetup (Waterloo): Making Agentic AI Enterprise-Ready, the Memory and Context Challenge

Welcome to the AI meetup in Waterloo, in collaboration with AICamp, Google, n8n and Moorcheh.ai by Edge AI Innovations. Join us for deep dive tech talks on AI, GenAI, LLMs and Agents, hands-on experiences on code labs, workshops, and networking with speakers and fellow developers.

Agenda:

• 5:30pm~6:00pm: Check-in, food and networking
• 6:00pm~6:10pm: Welcome, Community update by AICamp
• 6:10pm~8:00pm: Tech talks and Q&A
• 8:00pm~8:30pm: Open discussion, Mixer and Closing.

Tech Talk: Building Agentic Workflows with Gemma Speaker: Alex, Google Antigravity Team

As AI shifts from cloud-dependent APIs to localized, privacy-first execution, running models natively on-device is becoming a critical engineering priority. In this session, Alex from Google’s Antigravity team will explore how to leverage Google’s open-weight Gemma models alongside the Model Context Protocol (MCP) to build fast, secure, and fully autonomous workflows.

Tech Talk: Solving Silent Memory Conflicts in Multi-Agent Workflows

Speaker: Dr. Majid Fekri, CTO & Co-founder, Moorcheh.ai by Edge AI Innovations

When your support agent has a perfect memory, what happens when multiple agents collaborate and remember contradictory facts? We take n8n multi-agent orchestration to the next level. We will show you how open-source memory, Memanto, actively catches and resolves conflicting data—like when Claude Code and Codex disagree on architecture—before it corrupts your pipeline's decision-making.

Tech Talk: Beyond Passive Vector DBs: Powering Agents with Memanto's Open-Source Active Memory

Speaker: Tara Khani, CEO & Co-founder, Moorcheh.ai by Edge AI Innovations

As AI workflows transition from static RAG to autonomous coding agents (like Cursor and Claude Code), traditional vector databases introduce a catastrophic "RAM Tax" and passive retrieval bottlenecks. This session covers the architecture of Memanto, an open-source active memory agent built on an Information-Theoretic semantic engine. We will break down how to replace passive data ingestion with a three-primitive memory loop (remember, recall, answer) that gives agents persistent, cross-session context. We will demonstrate how Memanto achieves state-of-the-art accuracy on LongMemEval while running entirely on-premise, slashing infrastructure overhead by 90% and scaling to trillions of workloads without indexing delays.

Venue: SPUR Campus - Spur Innovation Center

Local and Global AI Community on Discord

Join us on Discord for local and global AI tech community

Join us on Github and try open-source memanto agentic memory, a product of Moorcheh.ai by Edge AI Innovations