Agent frameworks & infrastructure
Agent sandboxes & runtimes
1,721 agents · most starred first
Agent sandboxes & runtimes, page 14 of 18
The Genezio Code Interpreter is a Virtual Machine isolated environment for running Python generated by AI agents.
LangChain tools for instanode.dev — let AI agents provision ephemeral Postgres databases and webhook receivers
Kubernetes Agent Sandbox integration for LangChain Deep Agents
A LangChain adapter for KernelBox, enabling stateful IPython execution.
Kubernetes sandbox provider for the DeepAgents framework
A LangChain sandbox tool that runs agent-generated code inside Kubernetes pods
Leap0 sandbox integration for Deep Agents
Modal sandbox integration for Deep Agents
Monza sandbox integration for LangChain Deep Agents
OS-enforced sandbox backend for LangChain Deep Agents using Landlock (Linux) and Seatbelt (macOS)
Novita sandbox backend integration for LangChain Deep Agents
PPIO sandbox integration for Deep Agents
JavaScript REPL middleware for deepagents
Runloop sandbox integration for Deep Agents
Run LangChain/LangGraph agents autonomously with webhooks, cron, and HTTP triggers
LangChain Sandbox
SandrPod sandbox integration for Deep Agents
Langchain Serve - serve your langchain apps on Jina AI Cloud.
LangChain integration for SkillLite - Lightweight sandboxed Python skill execution engine
LangChain Sandbox
Inmem implementation for the LangGraph API server.
Open-source alternative to langgraph-runtime-inmem
Temporal integration for LangGraph - durable execution for stateful AI agents.
LlamaIndex store wrappers that auto-provision Docker containers via py-dockerdb
llama-index Amazon Bedrock AgentCore Runtime and Tools integration
llama-index tools azure dynamic sessions integration for code interpreter
llama-index tools code_interpreter integration
python code executor tool that takes fuzzy input text to extract and execute code designed for LLM applications
Production-ready filesystem access tools for LLMs with TOCTOU protection
Effortlessly run LLM backends, APIs, frontends, and services with one command.
A lightweight framework that connects LLMs to a virtual computer (Docker-based sandbox) to build general-purpose agents
Run a IPython interpreter in the LLM virtual environment
Deterministic VM for LLM program execution
Run a Python interpreter in the LLM virtual environment
Secure Python code execution sandbox for LLM-generated code
LLM Sandbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated mode.
Production-grade security sandbox for executing untrusted Python & JavaScript code generated by LLMs using WebAssembly and WASI
Execute LLM-Generated Python Code Automatically
Isolated Python code execution with resource limits
Node execution agent for llm-port cluster-managed runtimes.
CLI installer and management tool for the llm.port platform
Server-side agent for loft-cli — executes plans locally on managed servers
Madpod Agent — AI agent runtime with Madpod control-plane channel
A Marimo concept fork with some support for LLM execution as cells
The High-Performance Local Runtime for Autonomous Agents
S3 client and NVMe-backed LRU cache for memrun
Minimal AI agent with Python sandbox for data analysis
A unified virtual filesystem for AI agents. Mount S3, Google Drive, Slack, Gmail, GitHub, Linear, Notion, Postgres, MongoDB, SSH, and more behind one filesystem so agents read, write, and pipe across services with familiar shell commands.
Run Claude Agent SDK agents in Modal sandboxes
LLM Sandbox is a lightweight and portable sandbox environment designed to run large language model (LLM) generated code in a safe and isolated mode.
Agents hosting adapter for Azure AI
Type annotations for boto3 BedrockAgentCore 1.44.7 service generated with mypy-boto3-builder 8.12.0
Server-side agent for nodeforge — executes plans locally on managed servers
Open source code interpreter agent
Open source code interpreter agent
An agent runtime for Python. Give your agent real work. Keep control: every action checked before it runs, every run survives a crash without silently redoing anything, every step on the record.
A lightweight, framework-agnostic safe code execution library for AI agents
A simple tool to deploy OpenAI Agents as FastAPI web services.
make python module as code interpreter tool for OpenAI Agent by MOSS protocol
Official Python SDK for OC Agents - Run AI agents programmatically
OpenHands Agent Server - REST/WebSocket interface for OpenHands AI Agent
The Unkillable, Local-First AI Agent Operating System.
The agent hypervisor: learned policy enforcement, zero-trust identity, execution sandboxing, and fleet intelligence for autonomous AI agents
Microkernel-style agent runtime — Pompeii-Agent
A production-ready runtime framework for agent applications, providing secure sandboxed execution environments and scalable deployment solutions with multi-framework support.
Python Dev Kit Inside Code Interpreter for AI Agents - Jupyter-based code execution with multimodal support
AgentOS Python SDK: run hosted agents, and report runs, events and spans from your own.
File storage and sandbox backends for AI agents
Filesystem sandbox toolset for PydanticAI agents with LLM-friendly errors
Persistent just-py-bash shell capability and toolset wrapper for Pydantic AI
Production runtime for pydantic-ai agents with structured event streaming, session persistence, and cancellation
Agent daemon for Remote AI Maestro — manages PTY sessions and AI agent subprocesses on remote machines
A library for interacting with Object Storage on Replit
Robocorp Asset Storage library
Let language models run code.
Shadow-Sandbox DB Layer -- let AI agents modify your database safely with tenant isolation, Pydantic validation, and atomic sync.
Run LLM agents inside disposable Docker sandboxes.
Python client SDK for Sandbox Agent — universal API for automatic coding agents in sandboxes
AutoGen code executor for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
CrewAI tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
LangChain tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
LlamaIndex tool for Sandflare Firecracker microVM sandboxes — run agent-generated code safely
Python SDK for running coding agents in sandbox backends
Declarative YAML-based framework for defining, managing, and orchestrating AI coding agent instances
Installer for the cmdop CLI — stand up an AI agent on a machine you already have
Runtime interface to running docker containers
sgx storage client
The in-guest agent for ShakenFist instances
A brief description of your package
Storage Client For Microservices
Storage Client For Microservices
Storage Client For Microservices
Capsule sandbox integration for smolagents — run code in isolated WebAssembly sandboxes
Sorna agent
Remote AI Command Center agent for NVIDIA DGX Spark