hermes-desktop
SHA-256Hermes Desktop is a native desktop app that provides a graphical interface for installing, configuring, and interacting with Hermes Agent, a self-improving AI assistant.
Smart Download
Download Download Version
v0.5.5 · 169.7 MB
A GUI desktop companion for Hermes Agent — install, configure, chat, and manage tools, memory, and messaging gateways.
Core Features
- Guided first-run install with dependency resolution (Git, uv, Python 3.11+)
- Local or remote backend mode (connect to 127.0.0.1:8642 or a remote Hermes API server)
- Streaming chat UI with SSE, tool progress indicators, markdown rendering, and syntax highlighting
- 22 slash commands (/new, /web, /image, /code, /shell, /usage, etc.)
- Session management with full-text search (SQLite FTS5), profile switching, and memory system
What It Can't Do
- •Windows installer is not code-signed, so SmartScreen may warn. For WSL users, the installer may stall if Playwright needs sudo without TTY; grant passwordless sudo temporarily. RPM builds on Fedora require --nogpgcheck and do not support auto-update.
Use Cases
- Manage a self-improving AI assistant as a local development companion with full GUI control over conversations, tools, and memory
- Integrate the AI into 16+ messaging platforms (Telegram, Discord, WhatsApp, etc.) for automated responses and scheduled tasks
Detailed Introduction
Hermes Desktop is a native desktop application that simplifies the setup and daily interaction with Hermes Agent, a self-improving AI assistant. Unlike generic AI chat clients, it offers a complete management suite: guided first-run installation, multi-provider support (OpenRouter, OpenAI, local endpoints), streaming chat with tool progress, token usage tracking, 22 slash commands, session management, profile switching, memory system, persona editor, scheduled tasks, and 16 messaging gateway integrations (Telegram, Discord, WhatsApp, etc.). It supports both local mode (runs Hermes on 127.0.0.1:8642) and remote mode (connect to a remote Hermes API server). Compared to tools like LM Studio or Ollama, Hermes Desktop provides a unified GUI for an autonomous agent with self-improvement capabilities, making it ideal for developers and power users who want a full-featured AI workspace.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Open the downloaded dmg file, then drag the app to Applications
Download the installer for your OS from the releases page (Windows: if SmartScreen warns, click 'More info' then 'Run anyway')
Run the installer and follow the wizard to choose local or remote mode, then configure an API provider or local model endpoint
Once setup completes, the main workspace opens — start chatting, managing sessions, tools, memory, and more
- Download the installer for your OS from the releases page (Windows: if SmartScreen warns, click 'More info' then 'Run anyway')
- Run the installer and follow the wizard to choose local or remote mode, then configure an API provider or local model endpoint
- Once setup completes, the main workspace opens — start chatting, managing sessions, tools, memory, and more
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
3d4faac14643838a9aae85d621622c049c4dfdc4968b819086da8a5e72fc4adbThis checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Uninstall the app via your OS normally. To remove all data, delete the ~/.hermes directory manually. On Windows, also check 'Settings > Apps' for residual files after uninstall.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
Vane
Privacy-first AI answer engine running fully on your hardware. Combines web search with local LLMs (Ollama) and cloud providers (OpenAI, Claude, Groq). All data stays local.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).