cd /news/ai-agents/walrus-sessions-8-building-chatbots-… · home topics ai-agents article
[ARTICLE · art-138746] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Walrus Sessions 8: Building chatbots that actually remember you ($2,500 in prizes, ends Oct 9)

A developer spent several days auditing MemWal, the open-source SDK behind Walrus Memory, reading through its auth layer, on-chain contract, and sample apps, and reported a couple of real bugs that maintainers fixed quickly. The work is tied to Walrus Sessions 8, a live hackathon session on building or retrofitting chatbots that persist context across sessions, users, and devices, with $2,500 in prizes ending October 9. The developer highlighted the SDK's constant-time auth checks, on-chain delegate-key verification, and quarantine/replay protection as a way to understand secure persistent agent memory under the hood.

by read1 min views3 publishedSep 24, 2026

Most chatbots forget everything the second a conversation ends. Ask it

something on Monday, come back Tuesday, and you're a stranger again.

Walrus Sessions 8: "Chatbots That Remember" is a live hackathon

session tackling exactly that — building (or retrofitting) a chatbot

that uses Walrus Memory to persist context across sessions, users,

and devices.

Build or retrofit a chatbot that:

Any use case counts: customer support, onboarding, tutoring, sales,

community bots, even game NPCs.

I spent a few days going deep on the underlying open-source SDK

(MemWal) — not just building with it, but actually reading through the

codebase: the auth layer, the on-chain contract, the sample apps. It's

a genuinely well-built system (constant-time auth checks, on-chain delegate-key verification, careful quarantine/replay protection), and

digging into how persistent memory is implemented securely taught me

more than most tutorials do. Ended up finding and reporting a couple of

real bugs along the way, which the maintainers fixed fast.

If you've ever wanted an excuse to actually understand how persistent, encrypted agent memory works under the hood instead of just calling an

API — this is a good one to dig into, whether you build the full

chatbot or just go bug-hunting in the SDK.

── more in #ai-agents 4 stories · sorted by recency
── more on @walrus memory 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/walrus-sessions-8-bu…] indexed:0 read:1min 2026-09-24 ·