Agent frameworks & infrastructure
Agent sandboxes & runtimes
1,721 agents · most starred first
Agent sandboxes & runtimes, page 16 of 18
a powerful agent os with great compatibility
The OpenCode harness connects `HarnessAgent` to OpenCode through a sandboxed bridge.
Safely run AI agents in Docker to control scientific experiments via MCP
Official TypeScript SDK for Stackbone — the marketplace and managed runtime for containerized AI agents.
Edge-native AI agent runtime — drives a virtual filesystem via any LLM (ai.libx.js). Same bytes run in node, browser, or edge.
Agentic Platform local execution runtime and CLI
Agentic Platform local execution runtime and CLI
AutoWonder local runtime — execute AI agent dispatch packages on your machine
Secure AI Agent Sandbox with Docker & eBPF interceptors
Feral Agent — proactive, portable AI agent with a native security sandbox
Durable provider-neutral AI agent runs, steps, checkpoints, budgets, leases, timers, effects, and handoffs.
Node.js bindings for the tinysandbox in-process AI agent sandbox
Programmatic AI agent runtime with pluggable providers and sandboxed virtual infrastructure
Interactive AI agent using GitHub Copilot SDK with Hyperlight sandboxed JS execution
An open-source, self-hosted server runtime for LangGraph.js agents in TypeScript. A drop-in replacement for the LangGraph CLI (dev/up/build/dockerfile).
Vercel platform World implementation for Workflow SDK
Helpers for running agent-browser inside sandbox runtimes
Docker-backed MycoMesh Provider launcher with the Consumer CLI compatibility entry point.
Node.js runtime adapters, workspace management, config, auth, and plugin support for afk-dev.
Secure agent runtime with trusted process mediation
_This package is **experimental**._
E2B sandbox backend for Vercel's Eve agent framework
The AI Agent Framework — sandboxed multi-agent orchestration, high-throughput stateful agents, modular agent session manager & runtime for pi / codex / claude
Agentic Platform local execution runtime and CLI
Snowline Portable Agentic OS - Companion layer for AI agents
Rust-native, API-first Agentic OS server (octos serve + bundled skills). Installs the prebuilt release bundle.
aihu compiler native addon (napi) — darwin-x64 platform binary.
aihu compiler native addon (napi) — linux-arm64-gnu platform binary.
Typed code-mode tool orchestration for LLM agents: tools become TypeScript declarations, generated programs are type-checked (routeable checker backends), repaired via diagnostics, and executed in a QuickJS sandbox.
workspace primitives for 3tears agents: workspace entities, sandbox, format handlers, tools
ARC — Agent Runtime Cockpit: Python daemon, adapters, context retrieval
Never worry about your AI agent breaking production again. Kill the process mid-flight — the wire transfer is still safely refunded, your database stays clean, and your users never lose trust. agent-saga is the 1-line bulletproof safety OS that turns unpredictable LLMs into crash-proof, enterprise-grade autonomous engines.
Portable Python contracts and clients for the agent-vm Tool Portal.
Partial managed Hermes profile adapter for agent-vm.
Docker sandboxes, tools, rewards and trajectories for RL post-training of LLM agents (TRL, verl, OpenRLHF, SkyRL, ART)
Zero-boilerplate deployment for AI agent frameworks — LangGraph, CrewAI, OpenAI Agents SDK, and custom agents
A secure, monetized Python sandbox for data optimization and Matplotlib rendering via x402.
Agent Runtime SDK for igentbase — build sandboxed AI agents with one import
A secure, self-hosted runtime for isolated AI agent execution
Feather durable execution platform — Python SDK
Feather durable execution platform — Python SDK
Python client for Amazon Bedrock AgentCore
Python client for Amazon Bedrock AgentCore Control
LangChain tools backed by cocoon microVM sandboxes
OpenAI Agents SDK sandbox provider backed by cocoon microVMs
Deep Agents sandbox backend for a locally-run OpenSandbox server
inis.run sandbox provider for the OpenAI Agents SDK (beta)
Pydantic AI toolset for inis.run sandboxes
inis.run sandbox provider for Strands Agents
Baponi sandbox provider for LangChain Deep Agents
inis.run sandbox backend for LangChain Deep Agents, plus a LangGraph recipe
Lightning AI sandbox integration for Deep Agents
Self-hosted LangSmith Deployments alternative: MIT Postgres+Redis runtime (edition=pg) for stock langgraph-api
Cage: run local-LLM components in a network-isolated OS process, hardware access intact, with a friction-free call interface back to the rest of your app.
Hardware-aware scheduler sidecar for OpenClaw
Runtime-agnostic governed agent execution — Community Edition
Sprites sandbox provider for the OpenAI Agents SDK
Local execution daemon for Tether Brain agent installations
Canonical LLM-facing URI process runtime — spec, executor, CI gates
CorvinOS is a secure, self-hosted platform that lets you run and manage AI agents directly on your own hardware. It keeps your data private while allowing you t
TypeScript SDK for the AfterQuery compute API — isolated sandboxes for AI agent pipelines
Rulvar isolated tool executors: reference ToolExecutorProvider adapters that run tool work out of process (subprocess and container) so hostile or model-generated scripts cannot reach host capabilities.
Run bounded, non-interactive jobs across agent harnesses with isolation, exact resume, and provenance
Policy-sandboxed runtime for AI agent processes: enforce a policy file, capture a tamper-evident trace, deterministically replay any run.
Secure local execution agent for Brinqz Cloud
OpenSandbox sandbox backend for LangChain deep agents
Run Claude Code in a throwaway Docker container.
Headless AI Agent Runtime — multi-host, MCP-compatible
Python SDK for AgentWay - runtime control plane for AI agents
Arkady's standalone agent runtime: hosts Agenton-composed Pydantic AI agent runs behind a FastAPI server, with knowledge, ask-human, and sandboxed shell layers.
The Operating System for AI Workers — build, deploy, and manage AI agents.
Daytona sandbox capability for Pydantic AI agents
AI-first sandboxed agentic development workbench — task orchestration, hierarchical memory, sandbox mediation, multi-agent parity, pluggable deployment.
Agentic OS local bridge — run dispatch, phase runner, Cursor adapter
Server-side TypeScript SDK for OpenPond sandboxes and agentic work
Aimform Compute — sandboxed tool execution, agentic actions, and workflow automation.
PostgreSQL Copy-On-Write for AI agent workspace isolation
Durable Agents for Agent Swarms, LLMs, and Autonomous Systems
Broker-backed, kubeconfig-free overlay for the Agentic Sandbox client.
A client library to interact with the Agentic Sandbox on Kubernetes (seamed republish).
OpenSandbox sandbox backend for LangChain Deep Agents — run agent-generated code and file operations in an isolated OpenSandbox environment.
Tianshu - Async AI Execution Platform
Pure-JS client and CLIs for Archil disks and sandboxes
QuickJS-backed code mode tool for AI SDK
TypeScript SDK for Axern agentic infrastructure and isolated sandboxes
A secure, provider-agnostic Python runtime for AI agent tool execution with policies, budgets, approvals, and audit trails.
IFED agent-side ABI: the ctypes bridge to the compiled C++ libtorch runtime
LangChain tool for executing untrusted code in Microsoft Hyperlight micro VMs (experimental, AI-generated)
Microsandbox integration for Deep Agents
Launch ephemeral agents for single tasks in OpenShell sandboxes.
Python client for the Sandbox Agents control-plane: agents, sandboxed sessions, streamed runs.
HostAgentics review: compare features, pricing, use cases, access model, and alternatives for this AI Agents Platform agent in 2026. Managed hosting for workflow engines and autonomous AI agents
Run coding agents in a per-project dev container sandbox.
Kernel-side runtime shim for Zero recursion
AI agent that streams JavaScript into a persistent sandboxed Node.js runtime
Local, observable computers for any compatible AI agent
A Linux-like container that runs entirely inside Node.js — POSIX shell, ~140 coreutils, Node.js and Python runtimes, virtual filesystem and networking. No Docker, no VM, no native modules.
Harness-agnostic agent execution engine: run Claude Code, Codex (app-server), and any ACP agent behind one interface with a normalized event stream, multi-turn sessions, and resume. Root export is the wire contract; /core, /server, /client are the seats.
Local HTTP/WebSocket runtime and production Studio server for Agentic Design Runtime.