portable-hermes-agent
Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker.
What is portable-hermes-agent?
Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.
Overview of portable-hermes-agent
What it is
Portable Hermes Agent is a portable AI agent desktop for Windows. It provides 100 tools, a graphical user interface, local model support via LM Studio, text-to-speech, music generation, ComfyUI integration, workflows, and a tool maker. No installation, Docker, or admin rights are required. It is built on NousResearch/hermes-agent (MIT License) with extensive customization for non-technical users.
Key features
- Dark-themed Tkinter GUI with multi-language support (English, Traditional Chinese, Simplified Chinese, Spanish) and runtime switching - Image attachment with thumbnails and vision model support - Guided mode that works offline using a built-in 1,054-line user guide - API key setup wizard with individual service configuration - Permissions panel with granular control over file, network, and system access - 100 tools across 20+ toolsets including LM Studio, Music, TTS, ComfyUI, Workflows, Tool Maker, Serper, GPU, and more - Three portable extension modules (TTS Server, Music Server, ComfyUI) that auto-install on first use - Workflow engine for chaining tool calls into automated pipelines with conditions, loops, parallel execution, and cron scheduling - Dynamic Tool Maker to create new tools at runtime by wrapping REST APIs or writing custom Python handlers
Use cases
- Non-technical users who want a portable AI agent without system dependencies - Running local AI models on Windows with an NVIDIA GPU (8GB+ VRAM)
- Using cloud AI models via OpenRouter (free tier available)
- Creating custom tools and automating multi-step workflows - Generating speech, music, or images using the built-in extension servers
Getting started
- Download the latest
portable-hermes-agent-v*.zipfrom Releases and extract to a normal folder (e.g.,C:UsersYourNamePortable-Hermes-Agent). 2. Double-clickSTART.batto launch. On first launch, it downloads embedded Python, dependencies, LM Studio SDK, and Node.js tools automatically. 3. Alternatively, runinstall.bator for PowerShell:powershell .scriptsinstall.ps14. To launch again, use:batch START.bat :: easiest GUI launch UPDATE.bat :: safest one-click update hermes_gui.bat :: GUI mode hermes.bat :: CLI mode5. Connect an AI model:
- Cloud (free): File > API Key Setup > OpenRouter, sign up, paste API key.
- Local (NVIDIA GPU): Download LM Studio, load a model, start server, then in GUI Tools > LM Studio load model and click 'Use for Chat'.
License and pricing
MIT License. Open source and free.
Based on the project's public README and repository metadata.