Agents in Context Toronto: a MongoDB Hackathon
Nov 14, 2026 · Toronto, Canada
We simulate real world agent to agent systems built on MongoDB, Langchain (harnesses) ready for use in production to defend all systems. A swarm of real AI…
suture is an incident-recovery agent that finishes the job even when its worker crashes mid-run. Cleaning up a leaked key takes a chain of writes across…
+1Venues play one playlist for everyone, and the apps that let guests shape the music keep their likes on view with no easy way to take them back. Musory: your…
Robots are starting to learn from people, and fleets can share what one robot learns with every other robot. Nobody can yet answer three questions: who taught…
Phylax Tower is a safety net for airport control towers. In March 2026 at LaGuardia, a jet was cleared to land, and two minutes later a fire truck was cleared…
+1New hires hit the ground at light speed. New devs lose their first days juggling broken setup guides, each solving the same problems alone. Day One finishes…
PayProof helps a small Canadian construction business check a supplier's bank-account change before paying an invoice. The Canadian Anti-Fraud Centre names…
# Bodega — Herd Immunity for AI Agents What if one AI agent could learn from being scammed and automatically protect every other agent in its…
AI agents forget — and when they do remember, nobody can prove what they stored, who could read it, or whether it was really deleted. Memory You Can Govern…
AI can build almost anything. What stays human is taste, the ability to choose problems worth solving, and most people express it through social media saves…
Phoenix is an agent that finishes the job. It knows what actually happened across external systems, and completes the work after crashes, timeouts, lost state…
RecallTrace is an AI memory debugging and governance platform that identifies outdated or misleading memories influencing an agent’s decisions through…
MemoryDelta checks whether a saved calculation still follows the applicable rule before an AI analyst reuses it. In our electricity emissions demo, an agent…
An online store's AI shopping assistant handles orders and refunds and remembers each customer's preferences, like which card refunds go to. It also remembers…
Scoped Memory Agent: agent memory you can govern and prove AI agents that remember are a liability unless someone can answer for that memory. If a…
Wilco is an AI ground controller you can trust
Traceback is a debugging agent that saves a fix as memory only after tests show it turns a failing test into a passing one. Memories live in MongoDB Atlas…
Readback is an agent for long, multi-step jobs that cross systems and people it does not control. It never marks a step done until a second source confirms…
Countersign is an MCP server that sits between AI agents and MongoDB Atlas. Agents never write to the database directly. Every change becomes a proposal…
PromptForge turns a loose spoken or typed request, like “build the signup page and keep it consistent with what we decided”, into a clear, cited brief for an…
+1Gatekeeper is an auditable financial operations (FinOps) AI agent that moves authorization, policy enforcement, and auditability out of fragile LLM prompts…
Ontara makes reporting community problems like potholes simple. Residents fill out one form, and an AI agent finds the responsible authority, handles…
Refund Guard is a voice AI agent that handles inbound refund calls and decides in real time whether to approve, escalate, or decline, using MongoDB Atlas…
Bedley is an autonomous AI property manager that handles tenant requests from start to finish. Using AI voice agents, Bedley can respond to maintenance…
Continuum is an AI care coordinator for the 30 days after a patient leaves the hospital, when follow-ups are most often missed. When a patient is discharged…
Outage Router is a nuclear outage risk tracking system. It is designed to warn planners about risks that have come up in historical outages, either planned or…
Load Path lets several AI agents plan and fund bridge repairs under a fixed budget, and makes every action auditable. Each tool call, by an agent or a person…
CONTEXT RETAIL is a governed operational memory platform designed for AI agents working in multi-location retail environments. Retail organizations generate…
Yes Chef is a shop sign you change by speaking. An agent turns each sentence into actions on the sign, the online menu and the register, but only after rules…
FixLoop prevents apartment maintenance teams from repeating failed repairs by turning technician field notes into verified, human-governed AI memory. How It…
Precedent — Every experiment should make the next one smarter. What if the next breakthrough in research didn't have to start from scratch? AI agents can…
Our project lets an AI agent act on your money today. About nine million Canadians already share their banking credentials with third parties. Banks are now…
Lore is a retail analyst agent whose shared memory is governed by people: corrections become versioned proposals a reviewer approves, and a replay proves the…
+1Governed Memory Layer — agent memory with a permission system, an expiry date, an undo button, and a receipt Governed Memory Layer answers the Memory You Can…
Early dementia usually takes the newest memories first, like who's coming over today or what you told someone ten minutes ago. An agent that remembers…
+1Receipts is an on-call agent that handles engineering alerts and remembers past incidents — with the governance a company needs before it could deploy one. An…
Yanli is an AI marketing agent that manages ad budgets for small and medium business owners, marketers and agencies across Facebook, Instagram, Google, TikTok…
Strata is a shared engineering memory platform for AI-powered development teams. Today, valuable decisions, technical discoveries, and project context get…
AuditGate is a customer support and refund agent built around a simple idea: an AI shouldn't be trusted to police itself with money. Instead of relying on…
MongoGov is governed long-term memory for a customer-support agent, built on MongoDB Atlas. Support runs on repeat questions, and the fix usually already…
ArchMind is an AI-powered codebase exploration and engineering knowledge platform that helps developers understand both how a system works and why it was…
Rocket Academy: FIRST CONTACT How do we prepare robots for places they cannot easily reach? FIRST CONTACT is a planetary robotics prototype that turns…
ScopeEnvelope is an AI agent gateway and orchestration framework designed to govern agent execution, enforce strict file-write boundaries, track token…
Mirror is a privacy-first AI interview coach built for the MongoDB Hackathon (Problem Statement Two: Memory You Can Govern). Traditional AI speech coaches…
Raceday Cover Agent makes sure every racehorse is insured before it leaves the stable. Buying raceday cover is a manual chore today, so owners miss it, and if…
Sundown is an offboarding agent that only marks access revoked when an independent probe proves the employee’s token is dead. It survives silent failures…
Greenlight is a governed AI agent for marketing compliance, built to solve the challenge of making AI agents auditable, controllable, and safe for enterprise…
Stash: agent memory across sessions, laptops, models and teammates. When an agent’s session ends, everything it learned is lost: what it tried, what worked…
SafeSpace is shared spatial memory for blind and low-vision people, built on MongoDB Atlas. Wearing Mentra Live glasses, a person asks "Robin, where is the…
Exactly Once: nothing counts without a receipt. AI agents that take real actions crash. LangGraph with MongoDB's checkpointer resumes after a crash by…
Reversal agent resolves disputed trip fees on MongoDB Atlas. It reads the complaint, walks the trip graph, recalls only the memories that actor is allowed to…
When a service fails, the impact spreads quickly across the tools people use every day. OpsRelay is an internal AI incident response tool that helps teams act…
+1Phone call demo: https://youtube.com/shorts/lbGS0rggzK8?si=p0gZP5freCBqkANK All Clear is a recall agent with phone call feature that will not say "all clear"…
Market Council — Intelligence With Boundaries Category: Agents You Can Audit Tech Stack: MongoDB Atlas, Node.js, React, Finnhub API, Docker Project…
AI agents are great at starting work. They're bad at knowing whether it actually happened. Picture an agent paying out airline compensation. It sends a $700…
Warrant is a checkpoint between an AI agent and the money. Built solo, and everything was written today. THE PROBLEM. AI agents follow the rules. The damage…
FinishLine (Track 3: Finish the Job) is an autonomous release-closing agent built with MongoDB Atlas, Pydantic AI, LangSmith, FastAPI/SSE, and ElevenLabs…
Roadwatch is a web app for investigating public spending on road construction, built on the principle of evidence before conclusions. For any street in…
Scammers clone a grandson's voice or pretend to be the bank, and seniors send the money. In 2024, Canadians aged 60+ lost $137.9 million to fraud, and only…
memorydock is one governed memory for all your AI agents. Claude Code, the Claude app or any MCP client signs in via WorkOS OAuth to our FastAPI/FastMCP…
