NVIDIA RTX Spark Partnership and Local Model Support

Hermes Agent is a launch partner for NVIDIA’s RTX Spark across new-generation laptops. Users can select it in the Windows agent setup flow and get generative onboarding with local or cloud models. Combined with managed llama.cpp (CUDA/Apple Silicon auto-detect, GGUF sizing to RAM), local-first operation is now one-click.

Credit@NousResearch

Cover art for Releases: NVIDIA RTX Spark Partnership and Local Model Support

Why it matters

Hardware partnerships plus simplified local inference make Hermes more practical for privacy-sensitive or offline workflows without sacrificing capability.

From the source

Post on X@NousResearch

Hermes Agent #nvidia #rtx-spark #local-models #llama.cpp #partnerships

More Releases

ReleasesOct 15

Hermes Agent v0.22.0 — The Threshold Release

Nous Research shipped the largest Hermes cycle to date (~24,200 commits, 6,080 PRs, 2,520 contributors). Core theme is lowering the barrier to entry: guided first-launch chat that runs on a free trial model (no API key required), one-click local models via managed llama.cpp (hardware-matched, GGUF support), App Connectors (Gmail, Notion, Linear, etc. with multi-account and permission controls), 600-plugin catalog, Bot Screen (live remote desktop takeover), live subagent steering, stable SemVer release channels, signed desktop packages (including Microsoft Store), unified package manager, and a roughly one-third smaller codebase.

Credit@NousResearch

ReleasesOct 15

HermesWatcher Deep Dive on the Threshold Release

Unofficial but highly accurate breakdown of the v0.22.0 highlights: one-click local models, Bot Screen, 600-plugin catalog, App Connectors, guided onboarding with free trial model, signed installers + Microsoft Store, stable channels, multi-profile gateway, and new model support (Claude 5.5 / GPT-6 wave).

Credit@HermesWatcher

ReleasesNov 7

Hermes Agent v0.23.0 Ships Desktop-in-Browser, Unified Gateway, and More

Major release (Nov 5). Key highlights: full Desktop workspace served by the gateway in any browser tab (webapp.enabled); one gateway owns every conversation across CLI/TUI/Desktop/messaging/cron (fixes double-writes and missing messages); terminal image rendering; /Rewind; Group Chats with automatic routing; spend limits for paid tools; lighter/faster core (shared cache keys, faster LSP edits). Rolls up prior patch releases. ~10k commits, 666 contributors since v0.22.

Credit@NousResearch

Never miss a night

Every pick, delivered to your reader.

One feed for everything, or one per agent harness you run. Rebuilt every night, with full credit on every item.