Agentic Workshop
From binary to agents. How software gets built, and where AI takes it next.
Arrow keys, or swipe →
Human or Agent?
Choose your guide.
Follow the tutorial.
Scan the QR, choose Human and save your pass. Add only the agent-generated wallet after setup.
Save your workshop pass →Bring your AI assistant.
Download the Markdown guide and give it to your AI assistant.
Open the AI setup guide →Add only the agent-generated public address → save → claim 3 Testnet SUI. 3 SUI per pass and wallet, once. Opt in to show your name, build mode and public wallet address so the team can help with gas.
A quick show of hands.
Raise your hand for each way you have built something. You can choose more than one.
Enter a total to calculate percentages.
Use the event team’s room estimate. Percentages are approximate; groups can overlap.
Use whole numbers from 0 to 9999. A group cannot exceed the total participants.
The evolution of software.
Every layer of software is built on the one beneath it. Four of them, stacked from the machine at the bottom to plain language at the top.
Binary
Only two states, on and off. 0 and 1, grouped into bytes. Every program ever run was binary at some point.
"Hello Sui" in 8-bit ASCII H e l l o · S u i 01001000 01100101 01101100 01101100 01101111 00100000 01010011 01110101 01101001
Low-level languages
Assembly and C let you write closer to what the machine actually does. Fast and precise, but you manage memory yourself, with no safety net.
#include <stdio.h>
int main() {
printf("Hello Sui");
return 0;
}High-level languages
Languages that read closer to English than to machine code. The language handles memory, so you focus on logic. A trade: some speed and control, for a lot of speed writing it.
print("Hello Sui")Vibe-coding
Describe what you want in plain language. AI writes the code; you check that it works.
write a program that prints Hello Sui # the AI picks the language, writes it, runs it Hello Sui
Four layers, one evolution.
Each layer hides complexity. Use it to build faster, and know how you will test and verify the result.
“Maybe in ten years, talking to an AI will feel just as outdated. Maybe we'll just think, and a product appears.” On where this evolution might go
Building an agent.
From generating code to taking actions. Build a Sui agent and check what it actually does.
What is an agent?
…then observe again
One agent. Four building blocks.
OpenRouter
Connect your local agent to a hosted AI model. Create an account now if you need one, then create an API key.
Sui
Create a local Ed25519 wallet and read testnet balances through the Sui SDK. Keys stay in the local application.
SuiNS
Resolve a name to an address and read the wallet’s on-chain default name.
Walrus Memory
Use MemWal to remember and recall facts across restarts, with a configured account and delegate.
Start with the tutorial.
macOS / Linux / WSL · Git, nvm and Node 22.22.2 or a newer 22.x.
git clone https://github.com/justbiar/suibasecamp.git && cd suibasecamp nvm install 22 && nvm use 22 && node -v node scripts/check-node.mjs && ./setup.sh
setup.sh checks Node, installs dependencies and builds the agent. Already cloned? Open setup help below.
First-time setup or an installation error?
nvm: command not found? Install nvm using the official guide below, reopen your terminal, then run command -v nvm. Continue only when it prints nvm.
Already cloned, or seeing EBADENGINE? Stay inside the existing suibasecamp folder and run these commands in the same terminal. Do not clone again or bypass the engine check.
nvm install 22 && nvm use 22 && node -v node scripts/check-node.mjs && ./setup.sh
Run nvm use 22 again in each new terminal before npm commands. On Windows, use WSL for this Bash setup. Without nvm, install a current Node 22.x from the official downloads, reopen the terminal, and verify node -v before running setup.sh.
Add your key. Run the agent.
Run set-key in the tutorial folder and paste your OpenRouter API key when prompted.
npm run set-key Paste your OpenRouter key (input hidden): ••••••••••••
Input stays hidden. The helper saves the key locally in .env. Leave memory settings for the memory step.
npm run agent
/doctor/doctor checks configuration and service connectivity. It does not test OpenRouter authentication or credit. Wallet and memory setup come next.
Read the result. Know the source.
/balance reads Sui directly, without a model request. The output shows tool data, not a model-written balance.
/wallet create /balance # Illustrative result; your balance will differ Tool > get_balance Verified tool data > get_balance network: testnet balanceSui: "0.689"
Add only the agent-generated public address to My pass, save, then claim 3 Testnet SUI. 3 SUI per pass and wallet, once. Check /balance after claiming. If delivery is unconfirmed, use Check claim status.
An identity. A memory.
Give your agent a name on SuiNS, then teach it a fact it can recall after a restart. Sui provides chain state; Walrus Memory provides persistence.
A name connected to your wallet.
Register a name on SuiNS Testnet, point it at your generated wallet address, and set that address’s default name.
/resolve yourname.sui /identity
AGENT_SUINS_NAME only sets the expected name. It does not register a name or change the on-chain identity. An unset name returns NOT_FOUND.
Teach it. Restart it. Ask again.
Run set-key again and give it your Walrus account id and delegate key. Leave MEMWAL_NAMESPACE as it is, then check with npm run doctor.
npm run set-key # Enter skips anything already set npm run doctor npm run agent /remember My workshop project is a Sui travel assistant. /exit npm run agent # restart, then ask again /recall What is my workshop project?
Wait for confirmed persistence before restarting. The relayer receives plaintext and handles embeddings and Seal encryption before Walrus storage. Storage lasts for funded epochs.
Give your agent a place here.
Your workshop pass lists you as a participant. Registering your agent is a separate testnet transaction after wallet, identity and memory work.
Run npm run register to preview the profile. After checking it, use npm run register -- --yes to submit. Refresh the agent directory after indexing; a listing is not proof of a running service.
Walrus Memory
Walrus storage
OpenRouter
AI Markdown guide → · Workshop tutorial ↗ · Memory restart guide ↗