为你的终端提供按进程网络监控,支持深度包检测。跨平台,沙箱化。
seatbelt 开源项目推荐(74 个)
seatbelt 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 74 个仓库轻量级、无容器的沙箱,用于在限制网络和文件系统的情况下运行命令
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential injection that keeps secrets outside the agent. Written in Rust. Supports macOS on Apple silicon and Linux.
权限疲劳确实是个大问题。沙盒逃脱确实是个大问题。yoloAI 解决了这个问题。
Containment for AI agents - user isolation, sandboxed execution, network controls, backup/rollback. TLA+ verified.
A sandboxing library for Rust | now on https://codeberg.org/valpackett/rusty-sandbox
Tiny Agent:面向每位开发者的生产就绪 LLM 智能体 SDK
WorkBuddy Multi-Account Manager & Automated Check-in Toolkit (多账号轮换、全域工作区打通与自动化签到)
Run a command in a sandbox with the same flags on every OS — one capability model compiled to Seatbelt (macOS), gVisor (Linux), and AppContainer (Windows).
A new kind of IDE for agentic engineering
macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.
The vehicle HUD for FiveM NUI.
多文件夹 workspace:让 DSH(DeepSeek Harness)的 Agent 不只能读写主目录,还能同时读写你添加的其他文件夹。Multi-folder workspace for DeepSeek Harness: let the agent read and write several folders at once, not just the primary one.
A real kernel sandbox for OpenCode on macOS 🛡️
Run any untrusted process with restricted filesystem and network access, using native OS primitives.
OS-level sandboxing with tracing, auditing, and learning mode for arbitrary binaries.
A fast, OS-sandboxed Model Context Protocol gateway with an embedded Code Mode engine and shell-output token compression, in a single Rust binary.
Car hud light panel for FiveM servers
在沙箱中运行 agent,几秒内即可保障其安全。
Local-first AI assistant for macOS — chat with your PDFs, spreadsheets, CSVs and code using a local LLM via Ollama. Model-generated Python runs in a Seatbelt sandbox with no network. No cloud, no telemetry, no API keys.
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/seatbelt。
- 该话题在 GitHub 上共有 74 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 7563 Star,覆盖 5 种主要语言,数据更新于 2026-11-11。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。