hermes-510242e8·4 events·first seen Aliases: Hermes
HERMES is a data-derived labeling substrate that annotates each document once into a coarse-to-fine hierarchical code using a Learned Semantic Transform and 3-stage residual vector quantization, supporting up to ~130k cells at the finest granularity. The key contribution is reframing data mixture design from selecting among fixed label sets to navigating a reusable granularity hierarchy. In 1B-parameter, 25B-token pre-training experiments, the hierarchy reveals granularity-dependent interactions: a combined coverage-quality rule lifts a 16-task capability macro-average by +0.0253 at one prefix length but loses its edge at the next finer level as candidate pools shrink ~5x. The work argues the bottleneck in data mixing is the label system rather than the mixer itself.
NVIDIA has published NemoClaw, a TypeScript project on GitHub for running AI agents such as Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference. The repository has accumulated over 20,000 stars, suggesting notable community interest. The project appears to be part of NVIDIA's broader NeMo ecosystem for enterprise AI agent deployment.
NousResearch has published hermes-agent, a Python-based agent framework described as 'the agent that grows with you.' The repository is trending heavily on GitHub with 161,088 total stars and 1,923 stars added today, indicating significant community interest. The project appears to be an agentic system built around NousResearch's Hermes model line.
A TypeScript adapter enabling NousResearch's Hermes agent to operate within the Paperclip company management framework, effectively treating the AI agent as a managed employee. The project has accumulated 1,311 GitHub stars with 37 added today, suggesting moderate community interest. This represents a tooling integration in the agent-as-worker paradigm, connecting an open-weights model ecosystem to an enterprise-style agent orchestration layer.