# 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

Repository: https://github.com/shiwenwen/hope-agent
Canonical: https://ross.abutalabs.com/products/hope-agent
Language: Rust
License: MIT
License Family: permissive
Topics: agent, ai-assistant, anthropic, chatbot, claude, desktop-app, gemini, llm, local-ai, mcp, openai, claw, harness, ai, hermes-agent, personal, codex, openclaw, cross-device, handoff
Last push: 2026-08-26T07:21:38+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 12
- inputs: {"age_days": 173, "days_push": 7, "days_rel": 7, "gap_med": 2.0, "n_releases_24m": 43}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1501, forks 140 (observed 2026-08-28T04:04:54.290094+00:00)

## What it is
Hope Agent is a local-first, cross-device desktop AI assistant built with Rust and Tauri that features long-term memory, autonomous goal pursuit, and dynamic multi-agent workflow orchestration. It can also run headless as a persistent service on a NAS or cloud server via Docker.

## Use cases
- run a personal AI agent with long-term memory on my desktop
- hand off AI agent sessions across my devices
- deploy an AI assistant as a headless service on my NAS
- orchestrate multi-agent workflows dynamically
- use Claude, OpenAI, or Gemini models in one desktop assistant
- have an AI agent continue working on goals while I'm away
- self-host a personal AI assistant with Docker
- connect MCP tools to a desktop AI agent

## When to choose
- you want a polished, installable desktop AI agent rather than a CLI tool
- you need cross-device session handoff and long-term memory
- you want one assistant that can also run headless on a server or NAS
- you prefer a local-first, MIT-licensed agent supporting multiple LLM providers

## When to avoid
- you only need a simple chatbot without memory or autonomous goals
- you require production-grade stability on Linux or Windows, which are still experimental
- you need a lightweight library to embed agent capabilities in your own app
- you want a fully open model stack with no cloud LLM dependency

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, chatbot, chat-interface, mcp, llm-inference, gui, self-hosted
- domain: large-language-models, chatbots, desktop-applications, self-hosted, developer-tools
- platform: windows, cross-platform, rust, self-hosted
- tags: personal-ai-assistant, local-first, tauri, cross-device-handoff, autonomous-goals, long-term-memory, multi-agent-orchestration, headless-deployment, openai, anthropic, gemini, ai-agents, automation, macos, linux, desktop, docker, web-server

## Member repositories
- shiwenwen/hope-agent (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.290094+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:32:57.441670+00:00, confidence not recorded.
  - readme: https://github.com/shiwenwen/hope-agent (fetched 2026-08-28T04:04:54.290094+00:00, sha de0149899ff6)
- Data as of 2026-08-30T08:39:29.467469+00:00.