ME News reports that on April 5 (UTC+8), Jack Dorsey, co-founder of Block, posted about mesh-llm, a decentralized P2P inference project developed by Block employee Michael Neale, enabling users to pool their idle computing power to run large open-source models. mesh-llm supports mainstream open-source models such as GLM, Qwen3, DeepSeek, and Llama, is released under the MIT open-source license, provides an OpenAI-compatible API, and can be integrated with AI programming tools like goose and Claude Code. It is currently in experimental stage. (Source: Foresight News)
Jack Dorsey Introduces Block Employee’s Decentralized P2P Inference Project, mesh-llm
KuCoinFlashShare
Summary
Block co-founder Jack Dorsey announced a new project, mesh-llm, a decentralized peer-to-peer inference initiative developed by Block employee Michael Neale. The project enables users to combine idle computing power to run large open-source models, including GLM, Qwen3, DeepSeek, and Llama. It is licensed under the MIT open-source license and provides an OpenAI-compatible API. Details regarding project funding have not yet been disclosed, but the initiative aligns with Dorsey’s focus on decentralized infrastructure.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.