Tag
Hermes Agent ships 'Mixture of Agents', a feature that runs multiple frontier AI models in parallel and aggregates their outputs, reportedly outperforming individual models like Opus 4.8 and GPT 5.5 on internal benchmarks.
NousResearch announces that Hermes Agent now exposes Mixture-of-Agents (MoA) presets as virtual models, achieving 8% higher than Opus 4.8 and 11% higher than GPT 5.5 on an upcoming benchmark, providing capabilities beyond publicly available frontier models.
An unofficial browser extension for Hermes Agent has been released, allowing users to chat with Hermes in real time on any webpage's sidebar. It supports multiple model switching (Grok/GPT/Claude), visual analysis and screenshots, and connection to local or remote Gateway. A community open-source enhancement tool.
A tweet showcases Hermes Agent using computer control on a Mac with MiniMax M3 and Reachy Mini, demonstrating AI interacting with apps.
Hermes Browser Extension is an open-source Chrome/Edge side panel that connects to Hermes Agent runtime, enabling AI chat, model swapping, and browser context capture on any page.
A user reports that running Hermes Agent as a game master using DeepSeek V4 Flash locally on M3 Ultra yields nearly identical quality to the online version.
Hermes Agent by Nous Research introduces /learn, a command that lets the agent deliberately create skills from documentation, code, or instructions without needing to first fail at the task, turning any source into a reusable skill.
A developer demonstrates running Gemma 4 26B MoE model locally on an 8GB RTX 4060 with Hermes agent to fully automate backtesting of trading strategies, highlighting the growing capability of local LLMs as autonomous agents.
Demonstrates running Hermes Agent within an Apple container, highlighting compatibility and ease of deployment.
NousResearch's Hermes Agent team celebrates processing a trillion tokens per day and achieving 200k GitHub stars, highlighting their continuous improvement in AI agent development.
A walkthrough of Gbrain, a knowledge layer for AI agents that ingests meetings, chats, transcripts, and other data, enriching it with people and company info, and consolidating overnight.
Hermes Agent v0.17.0 now allows chatting via iMessage without needing a Mac. A quick setup video is provided.
A user expresses dissatisfaction with the Hermes Agent's appearance and UX, finding it sluggish compared to Pi mono agent despite its built-in features, and seeks others' experiences.
This article outlines a method to productize your expertise into a system using Obsidian and Hermes Agent, allowing clients to access your knowledge and frameworks without your direct time involvement.
Hermes Agent introduces a Blank Slate setup mode, allowing users to build an agent from scratch with minimal defaults.
Hermes Bible is a community-built, unofficial searchable documentation and workflow library for Hermes Agent, featuring 169 docs pages and 26 community flows with instant search.
Hermes Agent (from NousResearch) major version update adds support for Cursor's Composer mode, requires X Premium subscription, significantly improves coding capabilities.
Hermes Agent v0.17.0 adds standalone iMessage support without Mac relay, with faster response times than Telegram, and enables seamless communication.
A user reports running GLM 5.2 locally on a Mac Studio with 2-bit quantization, claiming it outperforms Opus 4.8 and enables free, private superintelligence for coding and agent tasks.
A migration guide for moving from OpenClaw to Hermes Agent, detailing the transfer of persona, memory, skills, and config files with options for preview, dry-run, and secret migration.