EKKOLearnAI/hermes-studio

Project overview

A desktop, web, and CLI application for running Hermes Agent conversations locally with multi-platform chat channel configuration, scheduled jobs, and administration. It supports text and audio interaction across Windows, macOS, and Linux with SQLite.

Project type

MCP · AI Agent · Workflow

Use cases

Knowledge Q&A · Automation

Deployment

Refer to project documentation

License

License pending

Best for

• Developers and AI engineers who need a local control plane to manage AI agent profiles, credentials, and multi-platform messaging channels from a single dashboard.
• General users who want a desktop application to run private agent conversations with voice input and text-to-speech capabilities.

Key capabilities

• Executes Hermes Agent conversations with persistent local sessions, configures platform channels, automates scheduled jobs, and manages group chats, skills, and files.
• Manages profiles, providers, models, credentials, memory, skills, plugins, logs, runtime settings, and MCP server administration from one interface.
• Offers unified configuration for 8 platforms: Telegram, Discord, Slack, WhatsApp, Matrix, Feishu, WeChat, and WeCom.
• Reads assistant replies aloud using multiple external providers and supports turn-based voice input.
• Provides an integrated terminal with PTY streaming, multi-session support, and file browsing across local, Docker, SSH, and Singularity backends.
• Functions as a native Electron shell for Windows, macOS, and Linux, bundling the Web UI runtime.

Limitations and risks

• External TTS providers may continue processing a request after the browser or server aborts.
• Custom and OpenAI-compatible base URLs must be public http/https endpoints and cannot target localhost or private networks.
• The system ships with default bootstrap credentials of admin / 123456 and requires users to change them after login.

Getting started

• Install the application using the pre-built desktop installer, npm CLI package, or Docker Compose. After installation, start the application or navigate to the local URL to access the dashboard.
• After logging in with the default bootstrap credentials, follow the prompt to change the admin password from the default to secure the local instance.

Evidence and sources

• GitHub project description: Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics
• README: A desktop app, local runtime, and web console for
• README: Configures platform channels, cron jobs, Kanban tasks, group-chat rooms, and MCP servers around the same Hermes profiles.
• README: Chat with agents, manage models and profiles, connect platform channels,
• Release: v0.6.30

Reviewed at: 2026-07-18T04:11:39Z