shiwenwen/hope-agent

🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手，也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment

What it solves

Hope Agent is a local-first, desktop-oriented personal AI agent designed to move beyond simple chat interfaces. It solves the problem of AI assistants being confined to a browser tab by providing a tool that can remember long-term context, autonomously execute complex goals in the background, and directly interact with the desktop and browser to perform actual work.

How it works

Built with Rust and Tauri, the project operates across three modes: a full Desktop GUI, a headless Server with a Web GUI, and an ACP mode for IDE integration. It uses a "Goal-Workflow-Loop" mental model where a Goal defines the outcome, a Workflow organizes the execution steps, and a Loop determines when to re-trigger tasks. It integrates with over 40 model providers (including local models via Ollama) and supports cross-platform memory management, MCP (Model Context Protocol) clients, and Docker sandboxing for secure tool execution.

Who it’s for

It is designed for power users who want a persistent AI assistant that can manage long-term projects, automate desktop tasks, and maintain a "second brain" of knowledge and design artifacts without relying solely on cloud-based chat bots.

Highlights

  • Autonomous Execution: Capable of breaking down goals into tasks and running them in the background with progress tracking.
  • Long-term Memory: Hierarchical memory (global, project, agent) with vector retrieval and "Dream Diary" synthesis to learn user preferences.
  • Desktop Control: Ability to observe and operate the macOS desktop, windows, and browsers (with user approval).
  • Design Space: Generates deliverable designs (web, mobile, PPT, etc.) from prompts or images with real-time preview and versioning.
  • Knowledge Space: A collaborative Markdown-based second brain that can sync with Obsidian.
  • Cross-Platform Presence: Syncs sessions and memory across desktop, web, and various IM channels like Telegram, Discord, and Slack.

Related

  • Project
    siddsachar/row-bot

    A local-first desktop AI assistant that uses agent orchestration and durable memory to perform complex work across local files, repositories, and external tools.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser workflows through a dedicated runtime engine.

  • Project
    Stack-Cairn/LiveAgent

    A local-first AI agent desktop client that integrates LLM reasoning with local system tools for file manipulation, command execution, and remote browser-based control.

  • Project
    hAcKlyc/MyAgents

    An open-source desktop workspace for personal AI agents that integrates local files, terminals, and a task scheduling system to move beyond simple chat interfaces.

  • Project
    proma-ai/Proma

    Proma is an open‑source, cross‑platform desktop AI agent that combines chat, planning, project‑based memory, and embedded tools (browser, terminal, calendar, Obsidian‑style markdown editor). It supports parallel sub‑sessions, skill bundles, and remote connectors (Slack, WeChat, etc.). Installable via binaries for macOS, Windows, and Linux; the open‑source edition requires user‑provided LLM APIs, while a commercial edition adds hosted model access, team management, and extra services. Licensed under AGPL‑3.0 with optional commercial licensing.