Cocos AI is a cutting-edge platform designed to enable secure multiparty computation (SMPC) using Confidential Computing and Trusted Execution Environments (TEEs).
It empowers organizations to collaboratively process sensitive data for AI/ML workloads while ensuring:
- 🔒 Data Privacy: Your data stays encrypted and secure throughout the computation.
- 🛡️ Trust and Integrity: Protected by hardware enclaves with robust remote attestation protocols.
- 🤝 Seamless Collaboration: Multiple organizations can work together without exposing sensitive information.
Cocos AI provides essential features for secure and efficient collaborative AI/ML:
- 🖥️ TEE Enablement and Monitoring: Secure VM management for deploying and monitoring workloads.
- 🛡️ Hardware Abstraction Layer (HAL): Built on a hardened Linux kernel, secure bootloader, and minimal root filesystem (minimal TCB).
- 🕵️ In-Enclave Agent and Networking Controller: Essential system software for managing secure workloads.
- 🔒 Encrypted Data Transfer: Asynchronous data transfer and secure result delivery.
- 🛠️ API for Platform Manipulation: Programmatic control for managing workloads.
- ✅ Attestation and Verification Tools: Hardware- and software-supported attestation for integrity assurance.
- 🖱️ Command-Line Interface (CLI): A user-friendly CLI for system interaction.
git clone git@github.com:ultravioletrs/cocos.git
makeThis will generate three binaries:
ls build/
# cocos-agent cocos-cli cocos-manager- Manager: Deploy on the AMD SEV-SNP host to orchestrate workloads.
- Agent: Build into the EOS-based HAL for secure enclave management.
- CLI: Interact with remote agents to control operations.
Comprehensive documentation is available at the official documentation page.
For CLI usage details, visit the CLI Documentation.
Documentation is automatically generated from the docs repository. Contributions to documentation are welcome!
Cocos AI is published under the permissive open-source Apache-2.0 license. Contributions are encouraged and appreciated!