AI Skill Hub 推荐使用:OS-Moda智能操作系统 是一款优质的AI工具。AI 综合评分 7.8 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
基于MCP协议的AI原生操作系统,支持Agent自主运行和自动化运维。核心特性是系统自我修复能力,AI可在无人值守情况下自动处理故障。适合需要自动化运维、AI Agent部署和智能自主决策的开发者和企业。
OS-Moda智能操作系统 是一款基于 Rust 开发的开源工具,专注于 MCP协议、AI Agent运行时、自动化运维 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。
基于MCP协议的AI原生操作系统,支持Agent自主运行和自动化运维。核心特性是系统自我修复能力,AI可在无人值守情况下自动处理故障。适合需要自动化运维、AI Agent部署和智能自主决策的开发者和企业。
OS-Moda智能操作系统 是一款基于 Rust 开发的开源工具,专注于 MCP协议、AI Agent运行时、自动化运维 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:cargo install(推荐) cargo install os-moda # 方式二:从源码编译 git clone https://github.com/bolivian-peru/os-moda cd os-moda cargo build --release # 二进制在 ./target/release/os-moda
# 查看帮助 os-moda --help # 基本运行 os-moda [options] <input> # 详细使用说明请查阅文档 # https://github.com/bolivian-peru/os-moda
# os-moda 配置说明 # 查看配置选项 os-moda --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export OS_MODA_CONFIG="/path/to/config.yml"
sandbox_exec exists, but bubblewrap isolation isn't fully wired for all third-party tools yet.capability_mint can create time-limited tokens, but socket authentication is still primarily file-permissions based.memory/recall uses FTS5 BM25 keyword search. Semantic vector search (usearch + fastembed) is designed but not yet wired.curl https://spawn.os.moda/.well-known/agent-card.json
osModa is a full NixOS operating system, not an app. It replaces your OS entirely — like installing Arch or Fedora, not like running apt install. It will NOT work inside Docker, LXC, or any container runtime. Containers lack systemd, NixOS package management, and the kernel-level access that osModa's 10 daemons require.
| Requirement | Details |
|---|---|
| **Platform** | Bare metal server, cloud VM (Hetzner, DigitalOcean, AWS), or QEMU/KVM virtual machine |
| **Architecture** | x86_64 or aarch64 |
| **RAM** | 2 GB minimum (4 GB recommended) |
| **Disk** | 20 GB minimum |
| **OS** | Fresh Ubuntu 22.04+, Debian 12+, or existing NixOS (installer converts to NixOS) |
| **NOT supported** | Docker, LXC, WSL, OpenVZ, or any container-based environment |
nix build .#nixosConfigurations.osmoda-dev.config.system.build.vm ./result/bin/run-osmoda-dev-vm -m 4096 -smp 4
git clone https://github.com/bolivian-peru/os-moda.git && cd os-moda
./scripts/deploy-hetzner.sh <server-ip> [ssh-key-path]
The gateway reads /var/lib/osmoda/config/agents.json at startup and on SIGHUP. Every chat session looks up its agent in that file, fetches the credential, and hands off to the right driver. Switching runtimes is a single PATCH:
curl -X PATCH -H "Authorization: Bearer $(cat /var/lib/osmoda/config/gateway-token)" \
-H "Content-Type: application/json" \
-d '{"runtime":"openclaw","model":"claude-opus-4-6"}' \
http://127.0.0.1:18789/config/agents/osmoda
systemctl reload osmoda-gateway # SIGHUP — in-flight sessions keep running
Or, from the spawn.os.moda dashboard, open a server → Engine tab → pick runtime / credential / model from dropdowns → Save. Same result; no SSH.
Credentials are encrypted at rest in credentials.json.enc (AES-256-GCM). Secrets never leave the gateway; the REST API returns a preview prefix only. POST /config/credentials/:id/test does a 1-token probe against the provider so you can validate before assigning.
The agent is tier 0 by design. It's not a chatbot with sudo — it's a system service with structured access to everything, constrained by NixOS atomicity and its own audit ledger, not by permission denials. Lower tiers cannot escalate privileges upward by design. Tier 0 remains the trusted computing base and must be governed by approval policies, spending limits, and audit review.
---
nix build .#nixosConfigurations.osmoda-iso.config.system.build.isoImage ```
Don't want to self-host? spawn.os.moda provisions a fully configured osModa server on Hetzner Cloud in ~10 minutes. Pick a plan, pay with card or USDC, and start chatting with your server from the browser or Telegram.
The dashboard shows real orchestration data from your server's daemons: active routines and watchers, audit event feed, learned system patterns, and running tool servers — all from live heartbeat data, not mocks. Manage agents directly from the dashboard: create new agents with model and channel routing, edit existing agents, or remove them — changes apply immediately on the server.
curl -fsSL https://raw.githubusercontent.com/bolivian-peru/os-moda/main/scripts/install.sh | sudo bash -s -- \ --runtime claude-code \ --default-model claude-opus-4-6 \ --credential "My Claude Pro|anthropic|oauth|$(printf 'sk-ant-oat01-…' | base64)"
imports = [ os-moda.nixosModules.default ]; services.osmoda.enable = true;
bash sudo nixos-rebuild switch curl -s --unix-socket /run/osmoda/agentd.sock http://localhost/health | jq ```
This is the primary install path. NixOS flakes give you reproducible builds, atomic upgrades, and instant rollback.
| Daemon | What it does | Key feature |
|---|---|---|
| **osmoda-keyd** | Crypto wallet daemon for AI agent workloads that need signing. AES-256-GCM encrypted keys, ETH + SOL. Policy-gated (daily limits, address allowlists). | Network-isolated (PrivateNetwork=true) — keys never leave the daemon |
Note: wallet/send signs an intent string, not a fully-encoded blockchain transaction. Broadcasting requires external tooling. See STATUS.md for details.
POST /wallet/create { chain: "ethereum"|"solana", label } → { id, address }
GET /wallet/list All wallets
POST /wallet/sign Policy-gated payload signing
POST /wallet/send Build signed intent (no broadcast — see STATUS.md)
---
curl -fsSL https://raw.githubusercontent.com/bolivian-peru/os-moda/main/scripts/install.sh | sudo bash -s -- \ --runtime claude-code \ --credential "Anthropic Console|anthropic|api_key|$(printf 'sk-ant-api03-…' | base64)"
curl -fsSL https://raw.githubusercontent.com/bolivian-peru/os-moda/main/scripts/install.sh | sudo bash -s -- \ --runtime openclaw \ --credential "Anthropic|anthropic|api_key|$(printf 'sk-ant-api03-…' | base64)" ```
Flags:
| Flag | Values | Notes |
|---|---|---|
--runtime | claude-code (default) / openclaw | Initial per-agent runtime. Changeable later from the dashboard without re-running this. |
--default-model | e.g. claude-opus-4-6, claude-sonnet-4-6 | Initial default for the osmoda agent. |
--credential | label\|provider\|type\|base64-secret | Repeatable. provider ∈ {anthropic, openai, openrouter, deepseek}; type ∈ {oauth, api_key}. |
--api-key | raw or base64 key | Legacy one-liner; auto-promotes to a credential. |
Every flag is optional — you can set all of this up from the dashboard afterwards.
Supported: Ubuntu 22.04+, Debian 12+, existing NixOS. x86_64 and aarch64.
Spawn osModa servers from code or from other AI agents via the v1 API with x402 payment:
```bash
创新的AI原生OS概念,MCP+Agent架构前沿。Rust语言保证性能和安全。但生态成熟度待考察,建议先在测试环境验证。
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,OS-Moda智能操作系统 是一款质量良好的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | os-moda |
| 原始描述 | 开源MCP工具:Your server fixes itself at 3am. You sleep. AI-native operating system built on 。⭐98 · Rust |
| Topics | MCP协议AI Agent运行时自动化运维自我修复Rust高性能 |
| GitHub | https://github.com/bolivian-peru/os-moda |
| License | Apache-2.0 |
| 语言 | Rust |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。