Nous Research releases Hermes Desktop, an open-source AI agent for every platform
Quick Answer
Nous Research has launched Hermes Desktop, an open-source AI agent app licensed under MIT, designed for cross-platform compatibility.
Quick Take
Nous Research has launched Hermes Desktop, an open-source AI agent app licensed under MIT, designed for cross-platform compatibility. This tool aims to enhance accessibility for developers and users alike, fostering innovation in AI applications across various environments.
Key Points
- Hermes Desktop is open-source and available under the MIT license.
- The app is designed for compatibility across multiple platforms.
- It aims to enhance accessibility for developers and users.
- The release encourages innovation in AI applications.
- Nous Research focuses on advancing AI technology through open-source solutions.
📖 Reader Mode
~1 min readNous Research has released Hermes Desktop, an open-source AI agent app under the MIT license. The desktop app is now available as a public preview for Windows, macOS, and Linux.
The agent runs across platforms including Telegram, Discord, Slack, WhatsApp, Signal, email, and the terminal. It has persistent memory that stores projects and solution paths, plus task planning in natural language.
Hermes can delegate to sub-agents with their own terminals and Python scripts, search the web, generate images, and read text aloud. Five backends are available for sandboxed execution: local, Docker, SSH, Singularity, and Modal. Through the Nous Portal, free and paid plans offer access to over 300 AI models. Documentation is available online.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
