Hope Agent

Hope Agent is a desktop AI assistant that can also run without a desktop interface on a NAS or cloud server. It's for people who want ongoing project work, memory and task state to carry across sessions and devices. It supports local model setup. Data stays on the hosting machine by default, while requests to remote models go directly to the selected provider.

Goals can continue in the background with visible progress, budgets, pause and resume controls. The agent breaks work into tasks, coordinates multiple agents and checks results against completion criteria. Recurring schedules can deliver results to a connected messaging channel.

Persistent memory retains project context and preferences, with detailed material retrieved when needed. Knowledge Space lets you and the agent edit the same Markdown notes, attach Obsidian vaults and trace information back to its sources. Completed work can become a draft skill for your review and reuse.

With permission and approval, the agent can operate the macOS desktop and browser, edit files, run commands and call MCP tools. Docker sandboxing limits tool execution, and a browser mirror shows the pages the agent is using.

Design Space creates websites, mobile prototypes and presentations from prompts or reference images. It includes visual editing, version history, exports and handoff to a code repository. Hope Agent is open source under MIT. Incognito sessions disable persistent memory and remove session data when the conversation ends.