# Osaurus — macOS AI Harness with Sandbox + MCP > Osaurus is a native macOS AI harness for agents, memory, and tools: run local/offline models, start a server/CLI, and expose tools via an MCP server. ## Install Merge the JSON below into your `.mcp.json`: ## Quick Use ```bash brew install --cask osaurus osaurus ui osaurus serve ``` ```json { "mcpServers": { "osaurus": { "command": "osaurus", "args": ["mcp"] } } } ``` ## Intro Osaurus is a native macOS AI harness for agents, memory, and tools—run offline local models or connect to cloud providers, then expose tools via an MCP server. The repo is GitHub-verified at 5,230★ and documents a brew cask install. **Best for:** macOS users who want one harness for agents + memory + tools across local and cloud models **Works with:** macOS Apple Silicon; local/offline models; OpenAI/Anthropic/Ollama-compatible APIs; MCP server mode **Setup time:** 15–30 minutes ### Key facts (verified) - README provides `brew install --cask osaurus` and `osaurus ui/serve/status` commands. - README notes sandboxed execution in an isolated Linux VM on macOS 26+ (Tahoe). - README lists MCP server config snippet: `command: osaurus` with args `["mcp"]`. - GitHub: 5,230 stars · 275 forks; pushed 2026-05-13 (GitHub API verified). ## Main If you are evaluating multiple models/providers, Osaurus helps because the harness (agents + memory + tools) stays constant while models change. A good first week plan: - Install and run the UI + server. - Create one agent with a dedicated working folder. - Turn on the sandbox only for tasks that need shell execution, and keep workloads separated per agent. Once stable, connect an MCP client so your other tools can reuse Osaurus-managed capabilities. ### README excerpt (verbatim)

Screenshot 2026-03-19 at 3 42 04 PM

Osaurus

Own your AI.
Agents, memory, tools, and identity that live on your Mac. Built purely in Swift. Fully offline. Open source.

Release Downloads License Stars

Platform OpenAI API Anthropic API Ollama API MCP Server Foundation Models Hugging Face PRs Welcome

Download for Mac · Docs · Models · Discord · Twitter · Plugin Registry

--- ## Inference is all you need. Everything else can be owned by you. ### FAQ **Q: Is Osaurus offline?** A: README says it works fully offline with local models, and can also connect to cloud providers when desired. **Q: How do I install it?** A: Install via `brew install --cask osaurus` or download the DMG from GitHub releases. **Q: How do I expose it via MCP?** A: Add an MCP server entry with `command: osaurus` and `args: ["mcp"]` per README. ## Source & Thanks > Source: https://github.com/osaurus-ai/osaurus > License: MIT > GitHub stars: 5,230 · forks: 275 --- ## 快速使用 ```bash brew install --cask osaurus osaurus ui osaurus serve ``` ```json { "mcpServers": { "osaurus": { "command": "osaurus", "args": ["mcp"] } } } ``` ## 简介 Osaurus 是原生 macOS 的 AI harness:集成 agent、记忆与工具,可离线跑本地模型或连接云端 provider,并通过 MCP server 暴露工具。仓库 GitHub 已验证 5,230★,并提供 brew cask 安装。 **最适合:** 想在 macOS 上用一个 harness 统一管理 agent、记忆与工具,并在本地/云模型间切换的用户 **适配:** macOS Apple Silicon;本地/离线模型;兼容多家 API;支持 MCP server 模式 **配置时间:** 15–30 分钟 ### 关键事实(已验证) - README 提供 `brew install --cask osaurus`,以及 `osaurus ui/serve/status` 命令。 - README 提到在 macOS 26+ 上可用隔离 Linux VM 作为沙箱执行环境。 - README 给出 MCP server 配置片段:`command: osaurus` + `args: ["mcp"]`。 - GitHub:5,230 stars · 275 forks;最近更新 2026-05-13(GitHub API 验证)。 ## 正文 当你在评估多个模型/Provider 时,Osaurus 的价值在于:模型可以换,但 harness(agent + 记忆 + 工具)不变。 建议第一周按步骤落地: - 安装并启动 UI + server。 - 创建一个带独立工作目录的 agent。 - 只有在需要执行 shell/编译等任务时再开启沙箱,并按 agent 维度隔离工作负载。 稳定后,再把它作为 MCP server 接入其他客户端,让你的工具链复用 Osaurus 的能力。 ### README 原文节选(verbatim)

Screenshot 2026-03-19 at 3 42 04 PM

Osaurus

Own your AI.
Agents, memory, tools, and identity that live on your Mac. Built purely in Swift. Fully offline. Open source.

Release Downloads License Stars

Platform OpenAI API Anthropic API Ollama API MCP Server Foundation Models Hugging Face PRs Welcome

Download for Mac · Docs · Models · Discord · Twitter · Plugin Registry

--- ## Inference is all you need. Everything else can be owned by you. ### FAQ **Osaurus 能离线用吗?** 答:README 表示可完全离线运行本地模型,也可在需要时连接云端 provider。 **怎么安装?** 答:按 README:`brew install --cask osaurus`,或从 GitHub Releases 下载 DMG。 **如何以 MCP 暴露?** 答:按 README:配置 `command: osaurus` 与 `args: ["mcp"]`。 ## 来源与感谢 > Source: https://github.com/osaurus-ai/osaurus > License: MIT > GitHub stars: 5,230 · forks: 275 --- Source: https://tokrepo.com/en/workflows/osaurus-macos-ai-harness-with-sandbox-mcp Author: MCP Hub