Image created with gemini-3.1-flash-image-preview with claude-opus-4.7. Image prompt: High-end product photograph of a classic banana split in a paper boat with three soft-serve scoops connected by drizzled chocolate and caramel threads forming a network mesh, sprinkle nodes along the sauce lines, bold serif ‘Nous Research’ lettering printed across the boat’s side, a small ’75 — Milford, DE’ embossed on the wooden spoon, soft directional studio light, glossy macro detail, shallow depth of field, landscape composition, Dairy Queen red and cream palette.
Happy to announce that Hermes Agent’s repo just surpassed Anthropic’s Claude Code repo
https://x.com/Teknium/status/2048710115885523444
@Teknium @NousResearch Feedback after running Hermes through Telegram for about 2 day: Experience is surprisingly good. Putting an agent on a VPS and talking to it through Telegram really does make it feel like I gave my AI coworker its own computer.
https://x.com/lizliz404/status/2049084890717806877
Hermes will now by default use native vision if the main agent model supports it, and you didn’t set a different vision auxiliary model! Just `hermes update` and it will take affect immediately. You can override this by setting any other model as your auxiliary vision model
https://x.com/Teknium/status/2048766822766547451
Nous Research shipped Hermes Agent v0.11.0, marking the framework’s largest update to date, fueled by over 700 pull requests from nearly 200 open-source contributors. The update introduces a completely rewritten, React-based terminal user interface (TUI v2) for better local
https://x.com/WesRoth/status/2047646749427216385
Want Hermes running in minutes? Follow this exact setup flow: 1. Install Hermes from GitHub 2. Launch it inside your terminal 3. Connect Obsidian as memory source 4. Sync OMI for automatic knowledge capture 5. Activate dashboard mission control 6. Create skills for repeatable
https://x.com/JulianGoldieSEO/status/2047699587788361844
GPT-5.5 and GPT-5.5 Pro are now available in Hermes Agent through the Nous Portal and OpenRouter providers! (alongside the direct openai oauth provider from yesterday)
https://x.com/Teknium/status/2047791512210293067
@Teknium WAY to early to call it yet, but so far @NousResearch Hermes is absolutely crushing @openclaw on proactively following instructions. Installed my first Hermes, and while the latest OpenClaw fails to follow a single task, Hermes crushed thru the entire workflow.
https://x.com/SecretArjun/status/2049006382763110639
My honest comparison of OpenClaw vs Hermes: LEARNING… > OpenClaw uses static, human authored skills. > Hermes refines skills with a self improvement loop. 👑 Hermes → (1-0) MEMORY… > OpenClaw has basic memory. > Hermes has multi-level memory and cross-session
https://x.com/LoicBerthelot/status/2047690512199540959
Leave a Reply