Liquid AI has unveiled a significant advancement in privacy-preserving AI workflows with the release of LocalCowork, an open-source desktop agent application powered by the newly introduced LFM2-24B-A2B model. This development marks a major step toward enabling enterprise-grade AI workloads to operate entirely on-device, eliminating the need for cloud-based API calls and reducing data egress—a critical feature for privacy-sensitive environments.
Introducing LFM2-24B-A2B and LocalCowork
The LFM2-24B-A2B model is specifically optimized for local execution, focusing on low-latency tool dispatching. It is designed to work seamlessly with the Model Context Protocol (MCP), a framework that facilitates secure and efficient interaction between AI agents and local tools. LocalCowork, available through Liquid AI’s Liquid4All GitHub Cookbook, allows users to deploy and manage privacy-first workflows directly on their machines.
Privacy and Performance at the Forefront
By enabling on-device processing, LocalCowork ensures that sensitive data never leaves the user’s machine, significantly reducing the risk of data breaches or unauthorized access. This approach is especially valuable for industries such as healthcare, finance, and government, where data privacy regulations are stringent. The architecture supports both local serving and flexible configuration options, allowing enterprises to customize the system according to their operational needs.
With this release, Liquid AI reinforces its commitment to democratizing AI while upholding privacy standards. The open-source nature of LocalCowork also invites collaboration and innovation from the broader developer community, potentially accelerating the adoption of local AI solutions across various sectors.
Conclusion
The launch of LocalCowork and LFM2-24B-A2B represents a pivotal moment in the evolution of privacy-preserving AI. As organizations grapple with increasing data security concerns, tools that enable local execution without compromising performance are becoming essential. Liquid AI’s latest offering not only meets this demand but also sets a new benchmark for secure, decentralized AI workflows.
