rabbitOS 2.3 integrates Nous Hermes Agent

// 1h agoPRODUCT UPDATE

rabbitOS 2.3 integrates Nous Hermes Agent

In the latest rabbitOS 2.3 OTA update, Rabbit Inc. has added native integration for Nous Research's autonomous Hermes Agent on the Rabbit R1. Users link their local Hermes Agent terminal via the Rabbithole web portal and swipe left on the R1 home screen to interact with the agent.

// ANALYSIS

While early reviews of the Rabbit R1 hardware were highly critical of its built-in features, outsourcing its interface to popular developer agents like Nous Research's Hermes is a brilliant pivot that transforms the R1 from a half-baked consumer gadget into a dedicated developer hardware deck for autonomous open-source AI agents.

* **Developer Pivot:** By supporting external open-source agents (Hermes, Claude Code, OpenClaw) rather than relying solely on their proprietary Large Action Model (LAM), Rabbit is repositioning the R1 as a physical controller/interface for developers.

* **Seamless Setup:** The integration bridges the local desktop environment (running the Hermes agent) and the mobile device via the Rabbithole portal ("nodes" interface), resolving the hardware's local compute limitations.

* **Open Source Win:** This gives Nous Research's Hermes Agent—popular for its robust long-term memory and autonomous task execution—a dedicated physical form factor, boosting real-world usage.

// TAGS

rabbitosrabbit-r1nous-researchhermes-agentagentopen-sourcehardware

DISCOVERED

1h ago

2026-07-11

PUBLISHED

2h ago

2026-07-11

RELEVANCE

7/ 10

AUTHOR

dominguezdaniel

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS46m ago

GPT-5.6 Sol Shares Fable 5 Vulnerabilities

OpenAI's latest flagship model, GPT-5.6 Sol, reportedly faces security concerns resembling those that led the Trump administration to impose temporary export controls on Anthropic's Fable 5 model. Amidst growing government scrutiny of frontier models and their ability to assist in cyber exploits, both companies are coordinating closely with federal bodies to mitigate national security risks, marking a major shift in how advanced AI releases are regulated.

LAUNCH1h ago

NVIDIA, LangChain launch secure NemoClaw blueprint

NVIDIA and LangChain have collaborated to release the "NemoClaw for LangChain Deep Agents" blueprint, an open-source reference stack designed to build, evaluate, and run autonomous enterprise AI agents safely. The stack combines NVIDIA's Nemotron 3 Ultra, LangChain's Deep Agents harness, and NVIDIA's OpenShell runtime to provide secure, sandboxed execution with kernel-level isolation, default-deny networking, and full infrastructure control.

OPEN SOURCE2h ago

Colibrì streams 744B GLM-5.2 from disk

Colibrì is a zero-dependency, pure-C inference engine that streams GLM-5.2 parameters from disk on demand, enabling standard PCs to run the 744B model. By keeping the dense model parts resident in RAM and streaming the massive routed experts from an NVMe SSD, it bypasses the need for high-end GPUs or massive RAM configurations.