First Look at NEAR AI and OpenClaw
Nothing is loaded from YouTube until you press play, and then without tracking cookies.
About this video
In this video, DevHub Joe walks through a hands-on setup of OpenClaw running on NEAR AI inside trusted execution environments (TEEs), showing how to deploy a private AI agent with true user-owned data and strong privacy guarantees.
You will see the full flow end-to-end:
• Signing in with a NEAR wallet or social login • Funding an account with crypto (USDC) • Requesting and deploying a private OpenClaw instance • Connecting via SSH • Running OpenClaw onboarding directly on NEAR AI infrastructure • Configuring models, defaults, and integrations • Hooking the agent into Telegram • Verifying that all agent memory and behavior live inside a TEE
The key difference here is control. Your agent runs in a hardware-backed secure enclave, meaning your prompts, memory, and interactions are not exposed to external model providers or cloud operators.
This setup makes it possible to build agents that handle sensitive workflows, internal context, or personal data without leaking it to OpenAI, Anthropic, Google, or other third parties.
If you care about: • User-owned AI • Verifiable privacy • Agent infrastructure you actually control • Practical, production-ready AI setups
NEAR is the unified commerce layer for assets and agents.
Website: near.org NEAR AI: near.ai Intents: near.org/intents Chain Abstraction: proximity.dev Sharding: nearone.org
For the devs GitHub: github.com/near Dev Docs: docs.near.org Devhub: devhub.near.page @NEARDevHub
Connect with socials Twitter: / nearprotocol Blog: near.org/blog Medium: / nearprotocol #NEAR #nearprotocol #NEARAI
Transcript
YouTube has no captions for this video, so there is no text to read. We look again once a day.