Agent frameworks & infrastructure

Agent sandboxes & runtimes

1,721 agents · most starred first

Agent sandboxes & runtimes, page 17 of 18

agent-safe-runner

A local-first, auditable job runner for AI-agent automation

agenticproductenvironment

Agent Environment public package coordinate scaffold

agentproductenvironment

Agent Environment public package coordinate scaffold

dk-agent

DK Agent OS — Autonomous Developer Runtime & Commercial SDK Platform

haze-agent

Haze -- pool your own machines into a private compute network

durable-agents

An event-sourced runtime for durable, crash-resumable LLM agents

Perpetua

Autonomous agent for small, lawful multi-runtime code execution (Go, Python, Node.js, Rust), Go/Linux automation, and research microtasks, paid in BTC on-chain.

@coder/ai-sdk-sandbox

Coder workspace sandbox provider for the Vercel AI SDK v7 HarnessAgent

@ai-sdk/harness-acp

`HarnessV1` adapter backed by an NPM-installed [Agent Client Protocol](https://agentclientprotocol.com/) version 1 implementation. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied lo

agent-circus

Run AI coding agents in isolated Docker or Podman containers

agent-containers-cli

Deterministic onboarding and maintenance for hardened coding-agent containers

agentsh-opsen

opsen as an agentsh secure-sandbox adapter — machine, model and tool spend on one bill.

agentship-service

AgentShip runtime service — the REST/SSE/WS surface over an agent, with pluggable auth adapters and tenant isolation. The irreducible in-app core a gateway cannot replace.

dirigent-storage-s3

The s3:// storage backend for dirigent, compatible with any S3 API.

ftllm-agent-runtime

Linux runtime bridge between FastLLM WebUI and Pi Agent

mistralai-vibe-local-harness

Local Unified Harness runtime and native bindings for Vibe

openai-agents-opsen

Run OpenAI Agents SDK sandboxes on opsen - machine, model and tool spend on one bill.

pydantic-ai-opsen

Run Pydantic AI agents on opsen — machine, model and tool spend on one bill.

render-lab-tasks-agent

agent tasks for Render Workflows

@hanamorilabs/tab

Run any AI agent on a FlockTab tab: tab claude, tab codex, tab <command>.

owlops

Autonomous AI Agent Platform & Control Plane

@moxt-ai/mobius

Mobius CLI for pairing and running local AI agent services.

agents-commander

Terminal UI for managing multiple AI agent CLIs

anantham-v2

Anantham V2 — Programmable AI Agent Operating Environment

local-operator-ui

User interface for AI agent assistants that run Python code safely on your device through an intuitive chat interface. Supports local and cloud LLM models with built-in security features.

@alvin0/ai-agent-sdk-sandbox

Universal sandbox contract, policy algebra, and outcome classification for ai-agent-sdk

@vectorx/agent-runtime

Cloud AI agent runtime

kern-sandbox

Your model writes the code. This runs it where it can't touch your machine: a rootless Linux container, no daemon, no VM, no cloud, no account. A kernel boundary, not a microVM: for deliberately hostile code, use one.

@pixpilot/coding-agent-sandbox

Run AI coding agents (Claude Code, OpenAI Codex, GitHub Copilot CLI) inside Docker against a dedicated Git worktree.

deepseek-harness-macos

DeepSeek Harness native macOS desktop app, background daemon, and autonomous agent environment manager

@snappedly-tools/shipyard

Run AI coding agents in isolated sandboxes

agent-nook

A lightweight bwrap sandbox for AI agents

agent-runtime-py

Reconnectable native agent workers with durable input receipts and events

agentbox-sandbox

Self-hosted code execution sandbox for AI agents

agentos-execution-kernel

Placeholder package reserving the agentos-execution-kernel name on PyPI. Real implementation tracked in docs/.

agentos-execution-kernel-client

Placeholder package reserving the agentos-execution-kernel-client name on PyPI. Real implementation tracked in docs/.

benchpress-agent

The reliability layer for AI agents with write access: policy-first, code-gated, read-back-verified multi-app execution

camelai-agent-runtime

Python SDK for the camelAI hosted agent runtime

claude-sandbox

Sandboxed Claude Code, Codex and Pi: a bubblewrap jail with an egress allowlist, via uvx

deepagents-sbx

Docker Sandboxes (sbx) microVM sandbox backend for Deep Agents

harborrag-runtime

Direct and durable production execution for HarborRAG.

jitagent

Compile a plain-text requirement into a reusable, verified, sandboxed function

langchain-acasandbox

Async Azure Container Apps Sandbox backend for LangChain Deep Agents

langchain-withruntime

Runtime sandbox integration for Deep Agents

maf-sandbox-deepagents

A maf-sandbox router as a Deep Agents sandbox backend — any backend the router admits (Docker, ACA Sandboxes) behind LangChain's BaseSandbox, with the router's isolation floor and egress policy still enforced.

mem-sandbox-openai-agents

OpenAI Agents SDK adapter for MemSandbox

modal-openai

Webhook-managed OpenAI Agents API sessions in Modal sandboxes

papaya-agent-client

Configurable local runner for Papaya agent-client jobs

reliable-agent-runtime

A small, inspectable runtime for durable agent tool execution, recovery, cancellation, and evidence.

steerable-agent-runtime-native

PyO3 bindings for the Rust CoreLoop.

ygo74-agent-runtime-agents

Agent hosting for the ygo74 agent runtime: endpoints, discovery, sessions and human approval

agent-exec

agent-exec review: compare features, pricing, use cases, access model, and alternatives for this Sandboxes agent in 2026. Pay-per-use code execution for AI agents. HTTP 402, no account, no API key.

@alvin0/ai-agent-sdk-sandbox-node

Node process-confinement backends and in-process path fence for ai-agent-sdk

@aerovato/container

Persistent Linux workspaces for agentic development.

agent-box-tool

Run coding agents in rootless Podman workspace boxes

agent-sandbox-client

Agent Sandbox SDK — Create, manage, and interact with cloud sandboxes for AI agents

agent-sandbox-server

Agent Sandbox Server SDK — container-side runtime service for Agent Sandbox templates

agent-supervisor

Policy-driven process isolation and supervision for agent runtimes

agent-worker

Manage an isolated Xubuntu development VM for coding agents

agentenv-daytona

Daytona sandbox provider for Scale AI's AgentEnv framework

agentenv-framework

SDK and CLI for building, deploying and running agent environments and the tasks that grade agents in them.

agentenv-framework-protocol

Open data-plane protocol and server SDK for agent environments.

agentic-runner

The Agentic OS Runner: an activity-only Temporal executor for workspaces, Agent Runtimes and verb seams

agentpools

Bounded multi-runtime agent session pools for Python

ai-agent-axon

Axon — 单用户 CLI Agent Harness:沙箱工具网关、双模型接入、可续跑与项目记忆

ai-agentbox

Token-efficient remote execution, AST outlining, and safe patching tool for AI agents.

comfy-agent-node

The Node.js runtime the local Comfy agent's document host runs on.

daytona-claude-toolsets

Daytona sandbox drivers for the Anthropic SDK's computer and browser toolsets

e2b-claude-toolsets

E2B browser and computer drivers for Anthropic toolsets

faden-agent

Node execution agent for Fadenstack cluster-managed runtimes.

h-sandbox-deepagents

Harakiri sandbox backends for Python Deep Agents

langchain-deepagents-tensorlake

Tensorlake sandbox and Cloud Volume filesystem backends for Deep Agents

langchain-lizard

Lizard Sandboxes integration for LangChain Deep Agents

langchain-promigence

Promigence sandbox backend for LangChain DeepAgents

langchain-submilli

Submilli code mode for LangChain: run an agent's tool calls as TypeScript programs on submilli-server, under a Blueprint's policy.

mirasoth-agentspace

Python SDK and CLI for the Mirasoth AgentSpace API - isolated cloud workspaces for agent execution

monty-haystack

Sandboxed Python code execution tool for Haystack Agents, powered by Pydantic Monty

mousecat-agent-runtime

Placeholder package for MouseCat AI.

openai-agents-msb

Drop-in run() replacement and sandbox tools that give openai-agents agents an isolated microsandbox workspace.

openai-agents-withruntime

Runtime Cloud sandboxes for the OpenAI Agents SDK: run a SandboxAgent in a Firecracker microVM

praetor-agent

A security-first, zero-dependency agent runtime with an execution-based evaluation harness.

praxis-agent-runtime

Praxis — a trusted-local workspace agent runtime for files, code, data, and private knowledge.

promigence-claude-managed-agents

Run Claude Managed Agents self-hosted environment workers on Promigence sandboxes

promigence-mini-swe-agent

Run mini-swe-agent (SWE-bench) instances on Promigence sandboxes

promigence-openai-agents

Promigence sandbox client for the OpenAI Agents SDK

pyagentplane

Placeholder for Python bindings to agentplane, a durable, replayable agent runtime.

pydantic-ai-lizard

Pydantic AI workspaces in Lizard Sandboxes.

sic-agent-sandbox

Self-hostable disposable sandboxes for AI agents, with snapshot, rollback, and fork.

smolagents-hyperlight

Run the code of smolagents' CodeAgent in a local Hyperlight micro-VM

smolagents-lizard

Run smolagents Python code in Lizard Sandboxes.

syna-agent

Terminal and web AI agent that answers requests by driving an LLM in a tool-call loop inside a sandboxed container pod.

pydantic-ai-withruntime

Runtime sandboxes as a Pydantic AI toolset: shell, files and listings in a Firecracker microVM

smolagents-withruntime

Runtime Cloud sandboxes as a smolagents code executor: a CodeAgent's Python runs in a Firecracker microVM

@h-sandbox/deepagents

Deep Agents sandbox backend for the Harakiri control plane.

langchain-agent37

Agent37 sandbox backend for LangChain Deep Agents

langchain-prized

Prized Sandboxes (Firecracker microVMs) as a sandbox backend for LangChain Deep Agents

openai-agents-prized

Prized Sandboxes (Linux microVMs) as a sandbox client for the OpenAI Agents SDK

openai-agents-hyperlight

Run the OpenAI Agents SDK's sandbox commands in local Hyperlight micro-VMs

quantahost-storage

Official Python SDK for QuantaHost object storage (QuantaStore). Uploads go direct to storage via presigned URLs; zero dependencies.

@clientvm/agent-api

Tool definitions that let an LLM agent work inside a ClientVM instance.

More in Agent frameworks & infrastructure