Agent Sandboxing & Infra
27 entriesSandbox environments and infrastructure for running AI agent code safely in isolated containers or micro-VMs.
AgentScope Runtime
assessPython FastAPI-based agent deployment runtime by Alibaba's Tongyi Lab with five sandbox types, Agent-as-a-Service stream...
AIO Sandbox
assessAn all-in-one Docker container bundling browser, shell, filesystem, VSCode Server, Jupyter, and MCP server into a single...
Amazon Bedrock AgentCore
assessAWS's fully managed platform for building, deploying, and operating production AI agents at scale, integrating sandboxed...
AnythingLLM
assessA self-hosted AI chat application with workspace-isolated RAG, a zero-config desktop app, and multi-provider LLM support...
Arrakis
assessSelf-hosted open-source sandbox platform using Cloud Hypervisor microVMs for secure AI agent code execution with native...
Cloud Hypervisor
assessOpen-source Rust-based Virtual Machine Monitor (VMM) for cloud workloads, maintained by Microsoft and Intel; offers more...
Codel
holdOpen-source autonomous AI coding agent (2024) that runs inside Docker with a web UI, executing tasks via terminal, brows...
CodeSandbox SDK
assessProgrammatic API for microVM sandboxes with snapshot, hibernation, and forking capabilities, now owned by Together AI.
Codex CLI
trialOpenAI's open-source terminal AI coding agent with OS-level sandboxing, subagent delegation, and AGENTS.md support.
ComputeSDK
assessA unified TypeScript abstraction layer for executing code in sandboxed environments across multiple cloud providers via...
Daytona
assessAn AI code sandbox platform with sub-90ms creation times, persistent Docker-based environments, and Computer Use support...
DeerFlow
assessA ByteDance SuperAgent harness that orchestrates specialized sub-agents for long-running tasks like deep research, code...
E2B
trialManaged cloud platform providing ephemeral Firecracker microVM sandboxes for AI agent code execution with sub-200ms cold...
Kubernetes Agent Sandbox
assessAn official Kubernetes SIG Apps project providing CRD-based sandboxed execution environments for AI agent workloads with...
Leash by StrongDM
assessContainer-based sandbox that monitors AI agent syscalls via eBPF and enforces access policies written in Cedar.
Microsandbox
assessA local-first sandbox platform running lightweight microVMs via libkrun with network-layer secret injection so credentia...
Modal
assessServerless Python infrastructure platform providing on-demand GPU and CPU compute with sub-second cold starts.
Northflank
assessEnterprise developer platform offering secure microVM sandboxes for AI agents with BYOC deployment and GPU support.
OpenHands
trialAn open-source platform for autonomous AI coding agents with Docker-sandboxed execution, multi-model support, and a Pyth...
OpenSandbox
assessA self-hosted sandbox platform by Alibaba for executing untrusted AI agent code, with multi-language SDKs and Docker/Kub...
Quilt
assessA Rust-based container infrastructure for AI agents providing instant parallel container creation with inter-container n...
Runloop
assessPersistent sandboxed dev environments for AI agents with git-style state management and built-in SWE-bench integration.
Sprites (Fly.io)
assessFly.io's persistent Firecracker microVM product with checkpoint/restore and auto-sleep billing for AI agent workloads.
Temporal
assessDurable workflow execution platform for building reliable distributed applications with automatic retry, state persisten...
Vercel AI Gateway
assessVercel's unified API proxy for 100+ AI models with budget controls, automatic failover, and no token markup.
Zeroboot
assessA research prototype providing sub-millisecond VM sandboxes for AI agents via copy-on-write forking of Firecracker micro...
Zerobox
assessA lightweight CLI and TypeScript SDK that sandboxes processes using OS-level isolation with deny-by-default file, networ...
Related Reviews
Arrakis: Self-Hosted MicroVM Sandboxing for AI Agent Code Execution
Abhishek Bhardwaj · Apr 20, 2026
Built for Humans, Consumed by Agents: The Next Decade of Sports Digital Platforms
Mark Shannon · Apr 20, 2026
Superpowers: An Agentic Skills Framework and Software Development Methodology
Jesse Vincent (obra) · Apr 20, 2026
Trigger.dev: Build and Deploy Fully-Managed AI Agents and Workflows
Trigger.dev Team · Apr 20, 2026
AgentScope Runtime: Production-Ready Agent Execution Framework by Alibaba Tongyi Lab
agentscope-ai (Tongyi Lab, Alibaba Inc.) · Apr 18, 2026