docker-sandbox

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

MCP-native security automation workbench (SDK + CLI + MCP) — authorized testing + static AI/MCP attack-surface self-audit to SARIF / GitHub Code Scanning

Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.

Run Pi coding agent isolated in a Docker Sandbox microVM with a local llama-server as the inference backend

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Custom template image for running pi inside Docker Sandboxes (sbx)

Warm, disposable GitHub Actions runners with Docker Sandboxes microVM isolation across Linux, macOS, and Windows hosts. Designed for teams that want to use their own compute for CI without running GitHub Actions jobs directly on the host.

AI-powered technical interview preparation platform with real-time voice conversations, live code execution sandbox, and comprehensive feedback. Built with LangGraph, LiveKit, FastAPI, and Next.js to simulate realistic interview scenarios with resume-tailored questions.

Local-first blue-team security platform. Scans code, secrets, dependencies, and databases in isolated local sandboxes, verifies fixes, and opens PRs to GitHub.

一个用 TypeScript 构建的多智能体学习与实验场：基于 DeepSeek Responses API，从零实现强类型 Agent Loop、工具调用回填、Skills 按需加载和 SQLite 会话持久化，并以 Gexep、Lexey、Jezeh 等角色“粘合”邮件、E2B Sandbox 等能力，以及对 MCP、A2A、最小权限协作和 GraphRAG 长期记忆的探索与思考。

Docker Sandbox template image for Pi coding agent

Computer use Docker Player (LLM Research)

AI Evaluation Mixin Kit for Docker Sandboxes (SBX). Run reproducible, isolated evaluation, benchmarking, and testing workflows with structured runtime evidence.

A tiny PHP sandbox powered by Docker

Local AI voice assistant powered by Whisper, Ollama, and edge-tts. Fully offline, no API keys.

This project allows you to run a lightweight, isolated Windows virtual machine using QEMU inside a Docker container, with VNC remote desktop access. It is useful for testing, sandboxing, or serving GUI-based environments remotely.

Next evolution of grounded evolution: evolves full agent blueprints (system prompt + tools + memory + planning + self-evaluation) using Docker sandboxing, multi-objective fitness, meta-evolution, and task specialization. Built using DeepSeek V4.

Securely run OpenCode AI agents with Ollama Cloud in a Docker Sandbox

Custom Docker Sandboxes Kits