🤝 OLLM x NEAR PROTOCOL PARTNERSHIP 🤝

Following yesterday’s momentum, we’re proud to announce another layer of trust for every user. Our mission has always been to merge intelligence, privacy, and verification into a single experience, and today marks another major step toward that goal:

🔸We’ve officially partnered with Near Protocol to integrate their confidential computing infrastructure directly into the OLLM Gateway. This collaboration represents what’s possible when leaders in private AI and secure computation come together to push the state of trust in AI forward.

🔹Users will be able to choose LLMs deployed on Near’s confidential computing infrastructure right from within OLLM. Every single request runs inside a Trusted Execution Environment (TEE) with real-time verification, powered by Intel TDX and NVIDIA confidential computing chips.

🔸Your data remains encrypted and isolated at every step, ensuring that no entity, not the model provider, not the infrastructure, not even us, can access it. The industry says “trust.” We say “verify.”

🔹Within the OLLM scanner, cryptographic attestation allows users to verify confidentiality on every request. Attestation is hardware‑verified and mathematically certain, eliminating blind trust and setting a new standard for transparency in AI inference.

🔸We’re incredibly excited to work alongside Near Protocol to make this a reality. Together, we’re building toward a future where confidentiality, proof, and performance coexist as core design principles. This is only the beginning.

Best,
The O Contributors