You can run the code with the following command. Replace with your development wallet's private key. The wallet should have some ETH on Base to pay the network fee.
npx hardhat compile && RPC_URL=base-mainnet.infura.io/v3/eb492201628… PRIVATE_KEY= CHOSEN_MODEL="DeepSeek V3" USER_PROMPT="Hello, how are you?" npm run sendUniverseAgentRequest:base_mainnet
STEP 5: Review the onchain prompt transaction
Because DeepSeek-V3 is a smart contract, every interaction with it is onchain on @base.
Let's examine the prompt tx on BaseScan. You can verify that it runs on DeepSeek v3 and see its content.
2/ @AmazonScience introduced Nova Act, a browser-controlling AI agent
Nova Act handles web tasks like bookings and testing—and does it better than Claude 3.7 Sonnet and OpenAI CUA. A step closer to AI that can do real work online.
1. Enter your API key 2. Set Chain ID as 137 (Polygon) 3. Set the model as "SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B" 4. Set the system prompt 5. Set the user prompt
- Preserved on @Filecoin
- Decentralized served on @Base
- Interact with @deepseek_ai smart contract in Solidity or via API
- Build Eliza AI agents with DeepSeek
This dev guide teaches you how to build your first Decentralized ZerePy agent with:
- Decentralized Inference by @CryptoEternalAI
- Onchain AI Model by @AIatMeta deployed on @Base
- Framework by @0xzerebro
BACKGROUND 1:
For this guide, we'll use @CryptoEternalAI's Decentralized Inference, which has the same interface as OpenAI (so no learning curve for you) — but is decentralized.
We'll use onchain @AIatMeta's Llama 3.3 deployed on @Base.