Every Hermes story we've covered — releases, tutorials, and analysis, summarised from the community and the official changelog. 118 and counting. New summaries are published as videos drop.
Looking for guides instead? See the Hermes hub.
Fahd Mirza serves Sage A1.5 locally, uses about 38 GB of VRAM, and tests it through Hermes Agent on a physics simulation and a three-sub-agent fact-check. Benchmark claims are the model card's, not independently run.
Tech With Tim walks through Hermes Agent from a one-click VPS deploy to Desktop, memory, personality, skills and Bot Mode. Checked against the Hermes docs, which differ from the video on the model command and on how Desktop signs in to a remote gateway.
The official Advanced Delegation plugin for Hermes adds model routes and profile routes to delegate_task. Requirements, the commands and the safety notes are taken from the plugin catalog; where the video differs, the catalog wins.
Hermes now lists an official Meshy plugin that turns text or images into 3D models and prepares them for printing. Requirements, the approval and credit limits and the data it sends come from the Hermes plugin catalog; the tool counts and prices in the video are labelled as the video's own.
A 15-minute walkthrough of running a free local model on a 64 GB Mac: pick a quantization that fits memory, load it in LM Studio, turn on its local server and add it to Hermes as a custom endpoint. Checked against the Hermes docs, which add a 64,000-token context requirement the video skips.
How Fahd Mirza prepares an LG or Android TV for a local Hermes agent running a Qwen model through Ollama: enable developer mode, find the IP, paste a prompt that asks before every change and keeps an undo list. Includes the Hermes and Ollama connection steps from the official docs.
What changed in Hermes Agent v0.22 (October 13): built-in local models through llama.cpp, a guided first-launch chat on a free trial model, connectors for Linear and Notion, password-manager logins the model never sees, a 600-plugin catalog, Bot Screen and a stable release channel. Checked against the official release notes.
A build-along that installs Hermes Agent on a 16 GB Mac mini with the macOS app, powers it with a local Gemma model through LM Studio (developer mode, 64K context, the /v1 URL), adds Honcho memory and Brave Search, connects Telegram through BotFather and schedules a daily news brief. Telegram steps checked against the Hermes docs.
Step 5 Preview as the model in Hermes Agent: the video's free-for-a-week claim, the 1M-token context a third-party listing shows, and what we could not confirm.
Perplexity's fast search is now the default web search for Hermes on the Nous Portal route. What changed, who gets it, and how to check an old web.backend setting isn't overriding it — checked against the Hermes docs.
A tour of the newest Hermes desktop features — one Bot per model, local models from Settings, the always-on-top HUD, voice and wake word, subagent views and cron jobs that remember past runs — with each claim checked against the Hermes docs.
Hermes agents can now get a dedicated desktop — screen, mouse, keyboard, browser and saved logins — on a headless Linux host, driven by the hermes computer-use screen command and schedulable like any other task.
Serena exposes language-server (LSP) code intelligence as 21 MCP tools. Installed with uv, registered in Hermes as an MCP server in ide-assistant mode scoped to one project, it found every reference to a column grouped by role, flagged a broken SQL join on its own, and renamed a function across the codebase in one operation.
Lessons from a month rebuilding the Hermes agent that runs a seven-figure business, covering customer support, product and marketing. The recurring theme is earning access rather than granting it, with deterministic guardrails doing the work that prompts cannot.
Hermes shipped /loop — a timer-driven wake-up that re-reads the world each tick and stops on a condition you set. Loop settings, a working deploy-watcher demo, and /loop vs /goal vs cron.
Terminal Bench 2.1 from 72 to 88, CyberGym 53 to 83 — and a broken three-service app fixed end to end through Hermes agent.
Nvidia's Nemotron 3.5 Lightning is a 30B MoE with 3B active parameters built for the execution layer of long-running agents. Serving it on vLLM needs Mamba-specific flags — here they are, plus a live bug-fix test driven through Hermes Agent.
Prime Agent keeps its own notebook and gets sharper alone; Hermes reads a vault every one of your agents can read. A side-by-side on how each learns, how each runs unattended, and which to reach for.
Apache 2.0, ~24GB quantized, built for tool-calling agents. The VRAM numbers, the KV-cache lever, and where Qwen still beats it.
A walkthrough of the Hermes v0.20 release: interruptible streaming speech, a wake word, an A2A protocol plugin, cited-source research, and a large latency cut.
Fahd Mirza wires Hermes agent into an Obsidian vault backed by a local Ollama model — no API key, no cloud. The agent creates, searches, links and reads markdown notes on its own machine.
Hermes Agent + four Apify actors + Airtable, packaged as a reusable skill and scheduled with cron — a scored lead list with a pitch already written for each business.
A Rust multiplexer for parallel coding agents — it reads agent state per pane and tells you which one is waiting on a decision, so you stop babysitting terminals.
A 124B MoE with 5.1B active params, free on OpenRouter — but it looped on a real four-bug debugging task inside Hermes. A candid hands-on test.
Hermes Agent v0.19 'Quicksilver' cuts cold-start from 4.3s to 0.9s, makes background jobs crash-durable via a database, and lets one gateway route channels to separate agent profiles.
How to point Hermes at Kimi K3 via the Moonshot provider, save reusable skills with /learn, and share a memory layer between the Kimi CLI and the Hermes agent.
A quiet Gemma 4 weight refresh fixed tool calling and the attention mismatch that crashed local runs — making a fully local Hermes setup viable.
Set GPT-5.6 Soul as your Hermes default, tune reasoning to medium, and three use cases: home AI lab, autonomous Unity game studio, and price-drop monitoring.
Hermes Cloud deploys an always-on agent that runs 24/7 on hosted servers instead of your laptop — name it, pick from 200+ models, launch in a sandboxed container in about a minute.
Models, multi-agent failover, platforms, cron cleanup, Tailscale, and reverse-prompting — Alex Finn's practical Hermes lessons.
A quick real-world test of screenshot-to-app in Hermes Agent using Sakana's Fugu Ultra orchestration model.
Seven new Hermes Agent features walked through — mixture-of-agents, /learn skill creation, /journey memory graph, cheaper self-improvement, git-controlled vibe coding, and a Fable 5 profile.
Fahd Mirza installs Headroom, a local proxy that compresses everything an agent reads before it hits the model, and wires it to a Hermes agent on Ollama.
Community Q&A on running an agent OS with Hermes: skill transfer from Claude, model fallback keys, Tailscale mobile access, and Netlify hosting.
A self-judging goal loop, proof-of-work coding verification, first-class mixture-of-agents, and new /learn, /journey, and background fan-out commands in Hermes V0.18.
A full Hermes agent walkthrough — skills, Telegram gateway, scheduled tasks, memory, profiles, and per-task model routing, plus what sets Hermes apart from OpenClaw.
Hands-on with Ornith — open agentic coding models built on Gemma and Qwen. Benchmarks, runtime setup for its reasoning/tool-call tags, and local use with OpenCode and Hermes.
Hermes Agent clicks and types in target apps without moving your cursor or pulling windows forward. Cross-platform, model-agnostic, with safety guardrails.
Eight Hermes changes: iMessage via Photon, automatic background sub-agents with a live tree, Unreal Engine 5.8 MCP, a revamped desktop app, profile builder, skills hub, smarter memory, and richer Telegram formatting.
Fahd Mirza installs a Pi-Reasoning fine-tune of Qwen 3.6 27B (Q4_K_M GGUF) with llama.cpp, wires it into Hermes agent, and tests it on bug-fixing, creative coding, and writing. The model uses baked-in multi-token prediction (MTP) plus speculative decoding for speed, fits in ~20GB of VRAM, and held up well on a real full-stack bug fix.
Fahd Mirza installs a coding-focused fine-tune of Gemma 4 12B — trained only on examples whose reasoning produced code that actually ran and passed tests — runs it locally with Ollama, and wires it into the Hermes agent. He puts it through three real tasks: fixing a tie-breaker bug in a World Cup tracker, generating an HTML animation from scratch, and optimizing a slow SQL query.
Hermes Agent + a local Gemma 4 12B model on a 16GB Mac Mini, set up end-to-end by Claude Code. The RAM-vs-context balancing act for local agents.
Two of China's strongest open coding models go head-to-head inside Hermes Agent on a real bug-fix-and-build task.
Fahd Mirza runs Kimi K2.7 Code inside the Hermes agent — a 256k-context MoE model that refactored a 4,000-file app and built five physics simulations from an image, from single prompts.
Fahd Mirza drives the new open-source Nex-N2 (Next N2 Pro/Mini) through the Hermes coding agent on OpenRouter, building a full-stack Django + React banking app with intentional bugs to fix.
The Hermes Agent OS renders your Obsidian vault as an interactive 3D star map. Hermes queries memory by date or topic, and agent conversations write new notes back automatically.
Hermes now includes an Idea Foundry pipeline where you submit an idea, agents classify and draft a plan, you approve at a single human gate, and sub-agents build the actual deliverable.
Google's Gemma 412B open model plugs into Hermes Agent OS as a free, local brain for full offline operation. Dual-brain setup, 16GB VRAM or free API.
Combining Claude with Hermes Agent gives Claude persistent memory across sessions via SQLite, an auto-improving skill system, and scheduled automation. Hermes can spawn Claude Code as a sub-agent, with Obsidian as a shared dashboard.
Build an agentic operating system where Claude and Hermes share a single Obsidian memory vault in a command center dashboard with Kanban, goals, journal, and content studio.
Hermes V0.16 walkthrough: connect Gmail via MCP for 24/7 email management, enable real-time voice with MiniMax M3, use Jarvis for hands-free computer control, and run multi-agent Kanban with a built-in goal judge.
Hermes V0.16 adds a central dashboard for skills, schedules, and model switching; Jarvis voice agent for hands-free commands; free Nvidia Nemotron-3 Ultra and Step 3.7 Flash models; a one-click skill browser; and a no-terminal desktop app.
How to use the Hermes V0.16 Skills Hub Browser to find skills from skills.sh, Claw Hub, Claw Marketplace, and GitHub; preview skill.md files before installing; run automated security scans; and manage installed skills by trust tier.
Hermes can now be called on the phone using ElevenLabs for voice and Twilio for the phone number, with Hermes acting as the brain that has memory, tools, and past sessions.
Hermes Agent 0.16 adds a native desktop app for macOS/Linux/Windows, remote gateway support, a full web dashboard admin panel, fuzzy model picker, /undo command, and major skill cleanup.
Fahd Mirza runs JetBrains' new Mellum 2 model locally via vLLM, connects it to an MCP filesystem server for real file operations, and tests it inside Hermes Agent.
Tech With Tim's complete beginner guide to Hermes Agent — VPS setup, memory system (user.md, memory.mmd), 90+ built-in skills, soul personality file, crons, and the self-improvement loop that makes Hermes better over time.
Hermes shipped a full browser-based admin panel — manage models, sessions, skills, cron jobs, API keys, and MCP tools without ever touching a terminal. Covers the new chat interface, model switching for rate-limit avoidance, one-click skill install, and mobile responsive design.
Hermes Desktop is now in public preview on Windows, Mac, and Linux. This overview covers all 7 key features: real-time work visibility, drag-and-drop files, voice mode, easy settings, the command center, and multi-agent coordination.
How to install Claude Code and Hermes Agent side by side, wire them into a single workflow, and use new features: parallel dynamic workflows, skill bundles, Bitwarden key storage, prompt injection guard, and push notifications.
Side-by-side comparison of Hermes and OpenClaw based on real usage: which is smoother, which has better docs, unique features like Hermes Kanban and persistent goals, and when to use both together.
Fahd Mirza walks through installing and launching Hermes Desktop on Ubuntu, configuring Ollama as the local model provider, and exploring the new GUI's themes, personas, MCP tools, and session management.
Alex Finn gives a complete tour of the Hermes Desktop app — organizing sessions, the Artifacts panel for links and files, skills token savings, cron job management, multi-agent profiles, and memory compression tuning.
Answers to common Hermes questions: how to run multiple simultaneous tasks with the Kanban board, using persistent goals for autonomous work, and wiring Obsidian as external memory for long-term context.
Julian Goldie demonstrates a voice-controlled Hermes agent powered by MiniMax M3, letting you control your entire AI setup through real-time conversation. Supports multiple voice styles, runs locally, and connects to your full agent memory and tool stack.
FuturMinds walks through a complete setup for automating an entire social media operation with Hermes agent using the Zo MCP — covering post creation, comment reply automation, WhatsApp lead qualification, and daily analytics from Telegram.
Hermes now ships an MCP catalog — a curated list of reviewed tools you can install with a single command instead of manually editing config files. Includes per-tool action whitelisting and parallel execution. (The video says tools auto-update; the Hermes docs say MCPs are never auto-updated.)
Fahd Mirza shows how DFlash's adaptive PFlash compression auto-tunes itself during Hermes agent sessions, cutting prefill from 3,572 tokens down to 148 — a 10× speedup with no manual config changes.
MiniMax M3, a new frontier-level agentic model from China, connects to Hermes agent via Ollama for free—giving Hermes a powerful brain for 12-hour autonomous tasks, local app control, web search, and scheduling.
Hermes Workspace is a community-built UI for Hermes agent that lets you add multiple AI models and launch agent swarms from one interface. This guide covers installation, OAuth model setup, and common sync issues.
Julian Goldie demonstrates how a custom Hermes Agent OS transforms scattered AI tools into a unified mission control dashboard with Kanban task boards, one-click MCP connections, and a shared Obsidian memory layer.
Combining Hermes agent with a custom Agent OS dashboard lets you access Claude, Gemini, and ChatGPT from one interface via OAuth—no separate API keys. One prompt triggers full multi-step workflows from research to publishing.
Three major Hermes updates: tool search auto-activates to boost accuracy from 49% to 74%, a built-in video agent powered by Hyperframes, and 30 days free of the Step 3.7 Flash model.
Julian Goldie answers community questions on Hermes: connecting Obsidian for personalized context, managing skills via Agent OS, creating named specialist profiles, and wiring Hermes into a Claude Code business dashboard.
Hermes v0.15 introduces automatic tool search that keeps only core tools in context and retrieves the rest on demand, raising tool-selection accuracy from 49% to 74% and enabling large toolsets without performance loss.
Wiring Hermes to an Obsidian vault creates a persistent memory layer where the agent already knows your goals, past tasks, and context on every run — and the vault is shared across Hermes, Claude, and OpenClaw.
Nous Research shipped a curated MCP catalog for Hermes that replaces manual config-file editing with an interactive picker. Tools are pre-reviewed, and you can allowlist or blocklist individual actions for fine-grained control.
Two free AI agents battle it out: OpenHuman offers instant no-code setup with auto-memory, while Hermes wins on customizability, MIT licensing, 200+ model support, and skill-based long-term memory.
Craig Hewitt, who runs two Hermes agents in production, debunks the six most common myths: you need a Mac mini, Hermes replaces Claude Code, build many agents, and more.
Hermes Agent v0.15 drops a velocity-focused release: 76% smaller codebase, sub-second startup, multi-agent Kanban swarms, 4500x faster search, and Bitwarden secret management.
Alex Finn's comprehensive Hermes Agent guide covers installation, model selection, when to use Hermes vs Claude Code vs Codex, /slashgoal, Kanban, self-improvement, and security best practices.
Alex Finn shares six Hermes Agent use cases from months of daily use: /slashgoal with metaprompting, Kanban board workflows, browser-based competitor research, and a personal memory wiki.
Julian Goldie demonstrates the Goldie Omnipresence Stack — a layered Hermes agent OS setup that auto-publishes SEO content, AI images, and videos across five websites simultaneously from a single keyword input.
Julian Goldie covers the Hermes update adding Grok 4.3's 1M-token context, pluggable video generation, /handoff model switching, 180x faster browser tool, Windows single-command install, and 22 messaging platforms.
Julian Goldie outlines 5 free Hermes configuration upgrades: Agent OS via soul.md, Kanban sub-agent teams, an AI SEO skill, hyperframe video templates, and goal-tracking with cron-based daily check-ins.
Alex Finn covers Hermes's 8 newest features: token-free session recall memory, /background multitasking, Grok 4.3 OAuth + X search, native Codex CLI integration, computer use, and AI video generation.
Full tutorial for deploying Hermes on a VPS to control WhatsApp groups through Telegram. Covers Hostinger one-click install, BotFather Telegram config, Periscope CRM MCP server setup, and automated briefings.
Owl Alpha on OpenRouter lets you run Hermes Agent at zero API cost. With a 1 million token context window and tool-use support, setup takes under 5 minutes via OpenRouter API key.
Alex Finn shows how to set up Hermes Agent backed by a local model on the NVIDIA DGX Spark, creating a private always-on AI employee. Hermes handles the full setup via a single prompt.
Nous Research added two free models to Hermes Agent: Qwen 3.6 Plus and Owl Alpha. Both run 24/7 tasks via the Nous Portal free tier with large context windows and no API costs.
Pareto Code from OpenRouter automatically picks the best coding model for each request. Combined with Hermes Agent, it routes tasks to whichever model scores highest — no manual model switching.
Hermes Agent provides planning and tool use; AionUI gives agents a desktop interface with eyes and hands. Together they run autonomously on your machine, chaining in multi-agent swarms — all data stays local.
Hermes Agent now supports 6 browser automation backends: cloud options (browser.com, browser-use, Firecraw) and local options (Camafox, Chrome DevTools Protocol, Agent Browser). Connect to your real Chrome with /browser connect.
Nate Herk takes Hermes Agent from zero to personal AI assistant: 91 built-in skills, voice responses, scheduled automations (crons), and a head-to-head comparison vs Claude Code and OpenClaw.
Hermes v0.13.0 ships a multi-agent Kanban board with hallucination gate, the /goal command for persistent task focus, session auto-resume, checkpoints v2, 8 security fixes, and new model support.
Hermes vs OpenClaw reliability breakdown, Telegram + Opus setup, self-improving skill system, two-agent local+cloud architecture, and practical use cases from Alex Finn.
Hermes Desktop v0.6.0: free Mac app with full Kanban board UI, file bookmarks for editing skills and memories, searchable pinnable chat workbench, all over SSH — no gateway layer needed.
Hermes dashboard and Kanban board walkthrough: run 30 parallel tasks with worker agents, set up a cheap librarian agent for Kanban management, and why OpenClaw's update cycle is driving users away.
Hermes Agent v1.3 launches Curator — it reads what you want, picks the best agents and tools for each subtask, chains their outputs, and improves its selections over time.
Hermes agent now integrates natively with LM Studio — local models are auto-discovered, loaded on demand, and Hermes picks the right reasoning level per model automatically.
Ollama's new 'ollama launch hermes' command sets up Hermes AI agent locally in seconds. Choose any local or cloud model, no config files, no API costs.
Anthropic's Claude Opus 4.7 pairs with Hermes, an open-source agent that writes reusable skill files after every task, creating an AI system that gets smarter the more you use it.
Craig Hewitt demos a Hermes + OpenClaw multi-agent architecture where Hermes acts as the always-on chief of staff and named OpenClaw sub-agents handle specific domains on a $9/month VPS.
Step-by-step Hermes agent setup using fully local and free tools: Ollama for model hosting (Gemma 4 E4B), self-hosted Firecrawl for web search.
A walkthrough of a self-assembled Hermes dashboard combining chat, voice, a task board, model switching and an Obsidian-backed shared memory.
A walkthrough of pairing Qwen 3.8 Max with Hermes as the agent harness — the model, harness and workflow-UI layer stack, Obsidian memory sync, and a lead-outreach workflow. No install steps or commands shown.
Julian Goldie describes wrapping Hermes in three layers — model, dashboard, and an Obsidian-based memory vault. Conceptual framing only; the build itself sits behind a paid community.
A three-layer 'agent operating system' around Hermes — models, a dashboard replacing terminal use, and an Obsidian memory vault.
Moonshot's Kimi K3 open-weights release, running it behind Hermes Agent, and what shipped in Hermes 0.19 'Quicksilver'.
Julian Goldie demos five Hermes Agent workflows — news radar, lead outreach, video generation, an SEO pipeline, and a builder-judge review loop — run from a dashboard. Demo of a paid bundle, not a reproducible install.
Julian Goldie demos the open-source Hyperframes skill (now with keyframes/arc motion) plus a Hermes-based video agent that scripts, generates B-roll, and assembles videos from one prompt.
Why local execution ties an AI coding agent to your computer staying on — and why a VPS is the fix for long-running and scheduled agent tasks.
Connect Hermes agent to LM Studio for fully local, free, private AI — no internet or subscription needed. Overview of the LM Studio + Hermes local setup.
The Hermes Skills Hub lets you search thousands of free skills from skills.sh, Claude Hub, Claude Marketplace, and GitHub, with one-click installation and built-in safety scanning.
Conceptual overview of building a custom 'agent operating system' around Hermes—unified memory via Obsidian vault, Kanban task boards, multi-model switching—instead of using the terminal directly. Analysis, not a setup guide.
Comparison of Odysseus (PewDiePie's new open-source AI agent) versus Hermes Agent for daily workflows.
Quick overview of connecting Google NotebookLM to Hermes agent via MCP, letting Hermes automatically convert PDFs, docs, and videos into podcasts, infographics, and slide decks with a single command.
Quick overview of running Hermes agent free by connecting the Step 3.7 Flash model (free for 30 days) through an agent OS — Hermes handles autonomous tasks like file access and background work at no cost.
← Back to the full news digest · Browse the Hermes guides