sandbox
Tracked open-source repos tagged sandbox, sorted by stars.
- #31
A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.
★ 2,842+3Star change over the last 7 days - #32
Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.
★ 2,821+6Star change over the last 7 days - #33
Runtime Security Enforcement System. Workload hardening/sandboxing and implementing least-permissive policies made easy leveraging LSMs (LSM-BPF, AppArmor).
★ 2,610+1Star change over the last 7 days - #34★ 2,440+1Star change over the last 7 days
- #35
A toolkit to make debugging iOS applications easier 🚀
★ 2,388+2Star change over the last 7 days - #36
Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
★ 2,343+1,711Star change over the last 7 days - #37
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
★ 2,296+11Star change over the last 7 days - #38
Run any Linux process in a secure, unprivileged sandbox using Landlock. Think firejail, but lightweight, user-friendly, and baked into the kernel.
★ 2,280+6Star change over the last 7 days - #39★ 2,236+59Star change over the last 7 days
- #40
The lightweight Arch Linux based distro that runs, without root privileges, on top of any other Linux distro.
★ 2,226+0Star change over the last 7 days - #41
A sandboxed JavaScript interpreter in JavaScript.
★ 2,185+0Star change over the last 7 days - #42★ 2,125+3Star change over the last 7 days
- #43
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.
★ 2,098+13Star change over the last 7 days - #44
Sandbox your local AI agents so they can read/write only what they need
★ 2,049+7Star change over the last 7 days - #45
📚 《Deep Agents 实战》—— LangChain 官方大使出品,基于 LangChain / LangGraph 生态,从零构建生产级 AI Agent 的完整指南
★ 1,857+43Star change over the last 7 days - #46
Generate sandboxes for C/C++ libraries automatically
★ 1,760+0Star change over the last 7 days - #47
Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.
★ 1,556+5Star change over the last 7 days - #48
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.
★ 1,533+1Star change over the last 7 days - #49★ 1,513+1Star change over the last 7 days
- #50
A multi-sandbox container runtime that provides cloud-native, all-scenario multiple sandbox container solutions.
★ 1,449+3Star change over the last 7 days - #51★ 1,354+8Star change over the last 7 days
- #52★ 1,351+5Star change over the last 7 days
- #53
DRAKVUF Sandbox - automated hypervisor-level malware analysis system
★ 1,338+3Star change over the last 7 days - #54
1 place to call all your agents - OpenCode, Hermes, Claude Managed Agents, Cursor Agents API, DeepAgents.
★ 1,268+29Star change over the last 7 days - #55★ 1,154+2Star change over the last 7 days
- #56
The Cloud Sandbox Built for AI Agents
★ 1,147-1Star change over the last 7 days - #57
Provide powerful tools for seccomp analysis
★ 1,135+2Star change over the last 7 days - #58
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
★ 1,131+33Star change over the last 7 days - #59
Run sandboxed code environments on Cloudflare's edge network
★ 1,125+5Star change over the last 7 days - #60★ 1,125+0Star change over the last 7 days