经 AI Skill Hub 精选评估,Heliox-OS Agent工作流 获评「推荐使用」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.2 分,适合有一定技术背景的用户使用。
隐私优先的开源AI系统控制代理,具有JARVIS级别的语音交互能力。支持自动化工作流、桌面应用、后台守护进程等功能,适合追求隐私、需要个性化AI助手的开发者和高级用户。
Heliox-OS Agent工作流 是一款基于 Python 开发的开源工具,专注于 AI代理、工作流自动化、语音交互 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
隐私优先的开源AI系统控制代理,具有JARVIS级别的语音交互能力。支持自动化工作流、桌面应用、后台守护进程等功能,适合追求隐私、需要个性化AI助手的开发者和高级用户。
Heliox-OS Agent工作流 是一款基于 Python 开发的开源工具,专注于 AI代理、工作流自动化、语音交互 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install heliox-os
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install heliox-os
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/VyomKulshrestha/Heliox-OS
cd Heliox-OS
pip install -e .
# 验证安装
python -c "import heliox_os; print('安装成功')"
# 命令行使用
heliox-os --help
# 基本用法
heliox-os input_file -o output_file
# Python 代码中调用
import heliox_os
# 示例
result = heliox_os.process("input")
print(result)
# heliox-os 配置文件示例(config.yml) app: name: "heliox-os" debug: false log_level: "INFO" # 运行时指定配置文件 heliox-os --config config.yml # 或通过环境变量配置 export HELIOX_OS_API_KEY="your-key" export HELIOX_OS_OUTPUT_DIR="./output"
<p align="center"> <a href="https://gssoc.girlscript.org/"><img src="https://img.shields.io/badge/GSSoC-2026-F96F59?style=for-the-badge" alt="GSSoC 2026"></a> <a href="https://github.com/VyomKulshrestha/Heliox-OS/releases"><img src="https://img.shields.io/github/v/release/VyomKulshrestha/Heliox-OS?style=for-the-badge&color=00f0ff&label=Release" alt="Release"></a> <a href="https://github.com/VyomKulshrestha/Heliox-OS/releases"><img src="https://img.shields.io/github/downloads/VyomKulshrestha/Heliox-OS/total?style=for-the-badge&color=7c6fe0&label=Downloads" alt="Downloads"></a> <a href="https://github.com/VyomKulshrestha/Heliox-OS/actions/workflows/release.yml"><img src="https://img.shields.io/github/actions/workflow/status/VyomKulshrestha/Heliox-OS/release.yml?style=for-the-badge&label=Build" alt="Build Status"></a> <a href="https://github.com/VyomKulshrestha/Heliox-OS/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/VyomKulshrestha/Heliox-OS/ci.yml?style=for-the-badge&label=CI&color=44cc11" alt="CI"></a> <a href="https://github.com/VyomKulshrestha/Heliox-OS/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22"><img src="https://img.shields.io/github/issues/VyomKulshrestha/Heliox-OS/good%20first%20issue?style=for-the-badge&color=purple&label=Good%20First%20Issues" alt="Good First Issues"></a> <a href="LICENSE"><img src="https://img.shields.io/github/license/VyomKulshrestha/Heliox-OS?style=for-the-badge&color=blue" alt="License"></a> <img src="https://img.shields.io/badge/Platform-Windows%20|%20macOS%20|%20Linux-333?style=for-the-badge" alt="Platform"> </p>
<p align="center"> <img src="https://raw.githubusercontent.com/VyomKulshrestha/Heliox-OS/main/assets/demo.gif" alt="Heliox OS Jarvis Demo" width="800"> </p>
<p align="center"> <strong>Control your entire computer with natural language, voice, and hand gestures.</strong><br> An open-source, privacy-first AI agent that plans, executes, and verifies complex multi-step tasks. </p>
<p align="center"> 🌐 <b><a href="https://helioxos.dev">Visit the Official Website (helioxos.dev)</a></b> 🌐 </p>
<p align="center"> <a href="#quick-start">Quick Start</a> • <a href="#-jarvis-mode-new">JARVIS Mode</a> • <a href="#features">Features</a> • <a href="#architecture">Architecture</a> • <a href="#security">Security</a> • <a href="#️-troubleshooting">Troubleshooting</a> • <a href="CONTRIBUTING.md">Contributing</a> </p>
---
Heliox OS now pushes the boundaries with 7 revolutionary biologically-inspired AI features powered by Meta's TRIBE v2 neural model:
print(f"Attention: {state.attention}, Stress: {state.stress}") print(f"Optimal: {state.optimal_interaction}") print(f"Overloaded: {state.is_overloaded}") print(hub.get_greeting()) # Adaptive greeting print(hub.get_offload_surface()) # Memory anchors ```
The easiest way to get started is to download the pre-compiled installer for your operating system.
1. Go to the GitHub Releases page. 2. Download the installer for your OS: - Windows: Heliox OS_x64-setup.exe - macOS (Apple Silicon): Heliox OS_aarch64.dmg - macOS (Intel): Heliox OS_x86_64.dmg - Linux: .AppImage or .deb 3. Install the app. 4. Open Heliox OS and enter your API Key (e.g., Gemini, OpenAI, Claude) in the Settings tab.
Note: The Python backend requires Python 3.11+ installed on your system. You must start the local daemon manually for now.
If you want to contribute or modify Heliox OS, build it from the source code:
1. Install the Python daemon:
git clone https://github.com/VyomKulshrestha/Heliox-OS.git
cd Heliox OS/daemon
pip install -e ".[full,dev]"
2. Choose your LLM: Local (Ollama): ollama pull llama3.1:8b -> ollama serve Cloud (Gemini/OpenAI/Claude): Add your API key in the app GUI.
3. Run the daemon:
cd daemon
python -m pilot.server
4. Run the frontend:
cd tauri-app/ui
npm install
npm run dev
Try clearing the npm cache and reinstalling dependencies:
npm cache clean --force
npm install
Also ensure that Node.js and npm are installed correctly.
---
"Show me my system info"
"Take a screenshot and read the text on screen"
"Go to Wikipedia's page on AI and summarize the first 3 paragraphs"
"Create a Python project with tests and run them"
"Kill the process using the most CPU"
"Monitor my CPU and alert me when it goes above 80%"
"Download a file and show me a tree of the folder"
"List all .py files on my Desktop"
"Set my volume to 50%"
"Create a CSV with sales data and analyze it"
"What's my IP address?"
"Install Firefox"
env_get · env_set · env_list
Config file: ~/.config/pilot/config.toml
[model]
provider = "ollama" # "ollama" | "cloud"
ollama_model = "llama3.1:8b"
cloud_provider = "gemini" # "gemini" | "openai" | "claude"
[security]
root_enabled = false
confirm_tier2 = true
unrestricted_shell = false
snapshot_on_destructive = true
[server]
host = "127.0.0.1"
port = 8785
If cloud models like Gemini, OpenAI, or Claude are not working: - Ensure your API key is added correctly in the application settings - Restart the application after updating the key
---
Heliox OS is now fully neuro-adaptive, integrating Meta's TRIBE v2 Cognitive Engine directly into the operating logic:
persona.md to align UIs to your brain.package_install · package_remove · package_update · package_search Auto-detects: winget, choco, brew, apt, dnf, pacman
Heliox OS ships with 3 flagship plugins and supports community-built extensions:
| Plugin | Type | Capabilities |
|---|---|---|
| **developer-tools** | Code | Jira tickets, git clone, branch, commit, push, GitHub PRs |
| **media-control** | System | Spotify (play/pause/skip), system volume, YouTube, media keys |
| **home-assistant** | IoT | Smart lights, switches, thermostats, scenes, device discovery |
Drop custom plugins into ~/.heliox/plugins/ — they're auto-discovered at startup after Ed25519 signature verification. Production registries can verify against bundled trusted public keys; local plugin packages can include plugin.ed25519.pub with plugin.ed25519.sig. Unsigned, untrusted, or tampered plugins are rejected before their manifest or code is loaded.
{
"name": "my-plugin",
"version": "1.0.0",
"tools": [{"name": "my_tool", "inputs": ["arg1"], "action_type": "api_call"}]
}
Heliox OS 是一款先进的 AI System Control Agent,旨在通过人工智能技术实现对操作系统的深度控制与智能化管理。它不仅是一个简单的助手,更是一个能够理解系统状态并执行复杂任务的智能代理,为用户提供全新的交互体验。
Heliox OS 引入了革命性的 TRIBE v2 认知特性(v0.6.0 版本),基于 Meta 的 TRIBE v2 神经模型,实现了受生物启发的 7 项核心 AI 功能。系统能够实时感知自身的 Attention(注意力)与 Stress(压力)状态,并根据交互负载自动调整行为,实现高度拟人化的自适应交互体验。
安装 Heliox OS 提供两种方式:1. 推荐方式:直接从 GitHub Releases 页面下载适用于 Windows、macOS (Apple Silicon/Intel) 或 Linux 的预编译安装包(如 .exe, .dmg, .AppImage)。2. 开发者方式:通过 Git 克隆源码,安装 Python daemon 环境,并根据需求选择本地 Ollama 模型或通过 API Key 配置 Cloud 模型(如 Gemini/OpenAI/Claude)。
Heliox OS 支持自然语言指令,用户可以通过对话执行多种复杂任务。例如:查询系统信息、截屏并识别文字、总结网页内容、创建并运行带有测试的 Python 项目、监控 CPU 使用率并设置阈值告警、管理系统音量以及执行文件操作等,极大提升了系统操作效率。
系统配置通过 `~/.config/pilot/config.toml` 文件进行管理。用户可以灵活配置 model 提供商(支持 ollama 或 cloud 模式)、指定具体的模型名称(如 llama3.1:8b)以及设置 security 安全权限(如 root_enabled 或 snapshot_on_destructive)。此外,系统支持通过 env_get、env_set 等命令进行环境变量的操作。
在使用 Gemini、OpenAI 或 Claude 等 Cloud 模型时,若遇到 API Key 错误,请确保已在应用程序的 Settings 设置中正确添加 Key,并在更新 Key 后重新启动应用程序以使配置生效。
Heliox OS 集成了 TRIBE v2 Cognitive Engine(v0.7.1),实现了神经自适应逻辑。通过 Neural Cognitive HUD,系统能实时追踪屏幕视觉缓冲区的 Saliency(显著性)与 Brain Load(脑负载),并映射至 Svelte UI。此外,系统具备动态 TTS Stress-Pacing 功能,并拥有强大的插件生态,包括支持 Git/Jira 的 developer-tools 插件以及支持 Spotify 的 media-control 插件,同时具备自动检测 winget、brew、apt 等包管理器的能力。
本章节提供故障排除(Troubleshooting)指南,帮助用户解决在使用过程中可能遇到的常见问题,确保 AI Agent 能够稳定运行。
开源AI代理项目,隐私设计理念先进,语音交互创新性强,但生态成熟度待提升,适合技术爱好者试验
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Heliox-OS Agent工作流 的核心功能完整,质量良好。对于AI爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | Heliox-OS |
| 原始描述 | 开源AI工作流:An open-source, privacy-first AI System Control Agent (JARVIS-like) using voice 。⭐28 · Python |
| Topics | AI代理工作流自动化语音交互隐私保护开源 |
| GitHub | https://github.com/VyomKulshrestha/Heliox-OS |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-16 · 更新时间:2026-05-24 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。