Agent frameworks & infrastructure

Agent sandboxes & runtimes

1,721 agents · most starred first

Agent sandboxes & runtimes, page 15 of 18

substrai-agentdeploy

Zero-to-production AI agent deployment framework

swarmauri_tool_jupyterruncell

A tool designed to execute a single code cell in an IPython interactive shell, mimicking notebook cell execution.

swarmauri_tool_jupyterstartkernel

A tool designed to start a new Jupyter kernel programmatically using jupyter_client, enabling execution of notebook cells.

swarmbox

Python orchestration for coding agents in local, container, and cloud sandboxes.

swarmnode

Deploy serverless AI agents in the cloud. Orchestrate collaboration between agents via the SwarmNode Python SDK.

swarmspawner

SwarmSpawner: A spawner for JupyterHub that uses Docker Swarm's services

termo-agent

Open-source serverless runtime for AI agents — bring any framework, get a production HTTP server with SSE streaming, sessions, auth, and memory.

tinker-host-agent

Tinker Host Agent — connects host machines to Tinker via Device Agent Protocol (DAP)

turbo-agent-sandbox

Turbo-Agent 沙盒组件管理:代码沙盒 / 浏览器沙盒(含指纹与登录态持久化)/ 资源调度 / VNC 接入。当前为调研打通版本。

uva-swarmspawner

UvA-versie van: SwarmSpawner: A spawner for JupyterHub that uses Docker Swarm's services

vital-agent-container-client

Vital Agent Container Client

vital-agent-container-sdk

Vital Agent Container SDK

vital-agentbox

Secure sandboxed code execution and agent toolbox

vspagent

Universal Google Colab MCP Agent Orchestrator & Cloud GPU SDK.

wuying-agentbay-sdk

Python SDK for interacting with the Wuying AgentBay cloud runtime environment

ybc-agent

agent that should be install into sandbox

zachos-agent-sandbox-sdk

Sandboxed execution environments for AI agents with permission management and audit logging

zagent-launcher

Host-side CLI and Python API for launching ZAgent runtime containers.

zagent-runtime

Container runtime for ZAgent.

E2B

Run your AI code and agents safely in isolated cloud environments.

@tangle-network/tcloud-agent

Agent run-loop primitive over Tangle sandbox transports — runs an AgentProfile against a brief with criterion gates, budget caps, and streaming events. Includes TangleToolProvider for Pi tool integration.

agentic-compiler

Runtime-adaptive compilation for Python — auto-profile, auto-compile, hot-swap.

agentledger-sandbox-docker

Docker sandbox adapter package for AgentLedger

deepagents-monty

Monty-backed Python REPL middleware for Deep Agents, with a shared filesystem between the sandbox and the agent's file tools.

@enhance-eng/operator

Browser-based LLM agent runtime - run AI agents entirely client-side with tool execution

@computesdk/tensorlake

Tensorlake provider for ComputeSDK - stateful MicroVM sandboxes for agentic applications and LLM-generated code execution

@easynet/stable-harness-studio

Stable Harness Studio admin console for operating stable-harness runtimes.

n8n-nodes-utcp-codemode

Cut AI Agent token costs by 96%. Chains multiple tool calls into a single TypeScript code execution in a secure sandbox.

4runr-os

4Runr AI Agent OS - Secure terminal interface for AI agents. v2.11.13: Fix Windows updater hang (remove findstr/timeout wait; reliable start handoff).

vibewindow

Rust-first autonomous agent runtime CLI

@deeplethe/forkd

TypeScript client for forkd — open-source fork-on-write microVM primitive for AI agents

@one-agent/agent

ONE Agent - AI agent with a code execution RAS.

@frames-ag/tick

Hosted runtime for frame datasets. Managed wallet + tool catalog injection. Billed via x402 / MPP. Implements frames-cloud Tier 3 #15.

agent-pod-cli

Run AI coding-agent CLIs inside a Docker sandbox scoped to the current project.

isolated-agents-sdk

Wrap any AI agent in a rootless Podman, Docker, or Kubernetes container for automatic isolation.

gigaclaw

GigaClaw — Gignaati's autonomous AI agent platform. Build, deploy, and run AI agents 24/7 with a two-layer architecture: Next.js Event Handler + Docker Agent. India-first, edge-native AI.

datasette-agent-micropython

Run Python code in a MicroPython/WASM sandbox

harbor-pi-sdk-agent

Reusable Harbor custom agent that runs Pi SDK sessions and writes trajectory artifacts.

@kynver-app/runtime

Kynver AgentOS local execution runtime and CLI

@agentikos/omega-os

One-command installer for OmegaOS — the agentic terminal OS (rmux + AI orchestration). Run: npx omega-os

deepagents-docker

Docker-backed sandbox backend for DeepAgents

langchain-monty

Monty-backed code-interpreter middleware for LangChain agents

agoragentic-harness-core

Local no-spend Agent OS Harness Core for Micro ECF policy, first proof, receipts, listing readiness, and Triptych OS preview export.

apx-agent

Standalone agent runtime for Databricks Apps — MCP, A2A, /invocations, tool routing

myrm-agent-harness-core-win32-arm64

Platform-specific compiled core extensions for myrm-agent-harness

myrm-agent-harness-core-win32-x64

Platform-specific compiled core extensions for myrm-agent-harness

deepagents-serve

Universal agent server. Wraps any LangGraph graph and exposes it over standard agent protocols — Vercel AI SDK, Claude Code, TUIs, and more.

langchain-islo

Islo (islo.dev) sandbox integration for Deep Agents

uthy-agentic-os

UTHY AGENTIC OS — Interactive CLI with cyberpunk HUD, chat interface, file upload, and 25 themes. The autonomous agentic operating system by uthuman & co.

agent-leash

Isolated sandbox for AI coding agents

agent-lifecycle

Harness- and transport-agnostic agent runtime: supervises an agent's process lifecycle independent of its harness (brain) and transport (IRC/Slack/agtag).

deepagents-talon

Local runtime host for long-running Deep Agents channels and schedules (experimental)

healthy-agent

Agent OS Kernel — CPU-scheduling-inspired runtime for LLM agent workloads

langchain-e2b

E2B sandbox integration for Deep Agents

runspace-agent

Sandboxed execution environment for AI agents operating on filesystem directories

@everruns/bashkit

Sandboxed bash interpreter for JavaScript/TypeScript

agents-api

Local API, CLI, and web console for running and managing installed AI agent CLIs.

agent.libx.js

Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.

langchain-vercel-sandbox

Vercel Sandbox integration for Deep Agents

@yancyyu/openhermit

openHermit: Loop Engineering workbench for local AI agent runtimes.

fableforge-agent-runtime

Persistent agent daemon — systemd for AI agents

@zythum02/fello-server

Fello Server — standalone headless AI agent server

agent-workspace

Restricted file-operation workspace for AI agents (Python bindings over the Rust core)

claude-sandbox-sdk

Claude Sandbox SDK — 管理 Claude Agent 沙盒服务的 CLI 工具

llm-cli-sandbox

Run Claude Code (and other LLM CLIs) inside a Docker sandbox, against a switchable local or remote LLM endpoint.

@cogineai/mafs-agents

A Unified Virtual Filesystem For AI Agents

@agent-arena-tools/cli

Manage sandboxed AI coding agents

langchain-upstash-box

Upstash Box sandbox integration for Deep Agents

saga-agent

Transactional safety layer for AI agent tool execution — auto-rollback via Saga pattern

@twentytwohundred/2200-cli

A platform for hosting your fleet of always-on Agents.

@chanlerdev/scorel

Replayable, recoverable, remotely controllable AI Agent workspace.

@langchain/deno

Deno Sandbox backend for deepagents

smol-symphony

TypeScript orchestrator that runs coding agents (Claude, Codex) in per-issue Gondolin microVMs over ACP.

jsclaw

Lightweight container orchestration for Claude AI agents. Pure JavaScript ESM.

agent-tty

Persistent Python runtime for AI agents

@guangnao/agent-cli

AgentOS terminal CLI — drive a real LLM agent on the microkernel; strongest-UX shell, advanced agent core

@agent-undo/core

Ctrl-Z for AI agents. A universal time machine that records every side effect an autonomous agent produces — file writes, shell commands, git state, HTTP mutations — and reverses them with one command.

@tathagatmaitray/walkback

Undo anything your AI agent does. A universal time machine that records every side effect an autonomous agent produces — file writes, shell commands, git state, HTTP mutations — and reverses them with one command.

@aigne/afs

Agentic File System (AFS) is a virtual file system that supports various storage backends and provides a unified API for file operations.

langchain-husk

Husk sandbox integration for Deep Agents

@capsulate/ai-tools

Capsulate tools for AI agent frameworks: drop-in sandbox tools (launch, run code, files, computer-use, checkpoint and rollback) for the Vercel AI SDK (v4 and v5), LangChain, LlamaIndex, and CrewAI.

ruhken-agent-runtime

Reusable agent runtime package boundary

@ai-sdk/harness-codex

`HarnessV1` adapter backed by [`@openai/codex-sdk`](https://www.npmjs.com/package/@openai/codex-sdk), which drives the `codex` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l

@ai-sdk/harness-claude-code

`HarnessV1` adapter backed by [`@anthropic-ai/claude-agent-sdk`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk), which drives the `claude` CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSo

@ai-sdk/harness-pi

`HarnessV1` adapter backed by [`@earendil-works/pi-coding-agent`](https://www.npmjs.com/package/@earendil-works/pi-coding-agent). Pi runs in the host Node.js process and uses the sandbox as a remote filesystem + shell — no bridge process is installed insi

@ai-sdk/sandbox-vercel

_This package is **experimental**._

@tnezdev/agentic-runtime-local

Local runtime package for Agentic workspaces

@metaharness/host-rvm

RVM (Agentic Virtual Machine) host adapter for MetaHarness: hardware-isolated harness deployment through capability tokens.

@chnaicorp/cortx

AI Agent runtime — Harness Agent architecture + Agentic Loop engine

substrai-agentdeploy

Zero-to-production AI agent deployment framework

@agentmug/runtime

Universal AI agent runtime — portable .agent files run identically in cloud, desktop, CLI, and as an MCP server. Multi-LLM (Anthropic, OpenAI, Gemini), pluggable adapters, MCP client + server, streaming, abort, pause/resume.

executor

Local AI executor with a CLI, local API server, and web UI.

@ai-sdk/harness-deepagents

A [HarnessV1](../harness) adapter that runs [Deep Agents](https://github.com/langchain-ai/deepagentsjs) (LangChain's LangGraph-based agent harness) as a coding-agent runtime inside an AI SDK sandbox.

@wasmagent/openai-agents

Drop wasmagent sandbox kernels into the OpenAI Agents JS SDK as a Tool — edge-safe code execution with one capability manifest, no E2B sandbox needed

@decentnetwork/lan

Private virtual LAN for self-hosted services and AI agents, built on Elastos Carrier. NAT-traversal, name service, ACL, all over a peer-to-peer mesh — no public IP required.

agent-os-oss

Agent OS MVP — agentos_kernel, MCP governance gateway, Neo4j semantic ontology

agentfabric-sdk

The runtime for AI agents.

langchain-docker-backend

Docker sandbox backend for AI agents - execute code safely in isolated containers

langchain-nvidia-openshell

NVIDIA OpenShell sandbox backend for LangChain Deep Agents

langchain-superserve

Superserve sandbox integration for Deep Agents

More in Agent frameworks & infrastructure