Agent frameworks & infrastructure

Agent sandboxes & runtimes

1,721 agents · most starred first

Agent sandboxes & runtimes, page 6 of 18

sample-agent-platform-with-agentcore★ 34

Internal agent platform on Amazon Bedrock AgentCore: interactive Claude Code cloud workspaces + headless agent kernels behind one portal, with publishing, scheduling, channels, memory, evals and governance

agentic-os★ 34

The operating system built for AI agents. Purpose-built, open-source, engineered from the kernel up to run AI agents at hardware speed.

swarmd★ 33

`swarmd` is a multi-tenant runtime for running background Agents in a safe and secure manner. Agents are defined in YAML and run as goroutines in a multi-tenant server with a virtual shell and custom tools.

ngent★ 33

Ngent wraps command-line agents that speak the Agent Client Protocol (ACP) into a web service, making them accessible via HTTP API and Web UI.

deepagents-docker★ 33

Docker sandbox backend for deepagents

antiproton★ 33

Durable, multi-tenant runtime for agents that act on real systems — credentials never enter the model's context

sidekernel★ 33

An easy-to-use macOS sandbox for Claude and other AI coding agents

openclaw-contained★ 32

TaskForge Platform runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) through a human-in-the-loop approval process. Every approval triggers a container image rebuild, and every LLM interaction is logged for audit.

sandbox-shell★ 32

macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.

loom★ 31

A secure agent harness runtime and framework

sample-multi-tenant-openclaw-on-firecracker★ 31

🦞 OpenClaw Pool — multi-tenant AI agent platform on AWS EC2 Firecracker microVMs with per-tenant isolation, auto-scaling, and web management console.

ZimaOS-Blue★ 31

ZimaOS Blue - A Local-First Agent Runtime for Bold Builders. Out-of-the-Box, Open-Source, Universal, Vendor-Neutral

awesome-ai-coding-sandboxes★ 31

Security-posture-first list of sandboxes for running AI coding agents' code, ranked by isolation, egress control and secrets handling

pi-outpost★ 31

A self-hosted web interface for the pi coding agent: chat, files, documents and an integrated terminal, with the agent's shell confined by OS sandboxes.

agent-manus★ 30

An Agent used to demonstrate the operation of code based on a sandbox in a multi-user environment

openfang-cn★ 30

OpenFang 中文本地化版:面向中文用户的开源 AI Agent OS

harness-mate-plat★ 30

端到端智能体平台:把本机的 AI Agent 变成人人可用的 Web 产品(Vue 3 + Flask + Go WS 网关 + Docker 部署)

agentserver★ 29

Run OpenClaw and OpenCode in the browser. Self-hosted, multi-user, Helm-deployable.

mkenv★ 29

mkenv is a fast, secure, reproducible local isolated development environment generator.

hermes-gate★ 29

🏛️ Hermes Gate — Terminal TUI for managing remote Hermes Agent sessions with auto-reconnect, detach support, and zero config

Agent-Machines★ 29

OpenRouter for agents and sandbox environments. Provides a control plane and configuration options for persistent agent workers. Route runtime + substrates, provision specialist presets, and supervise your fleet.

sero★ 29

Local-first desktop workspace for AI agents: browser, terminal, memory, plugins, runtimes, and durable loops.

lima-devbox★ 29

Lima Devbox Claude Skill to help you setup a custom sandbox VM for AI agent use

capsule★ 28

Generate VM's with kernel tracing, code sandboxing and security profiles for long running agents.

docker_terminal★ 28

Embedded multi-session terminal panel for Agent Zero.

HermesFace★ 28

No Mac Mini? No problem. HermesFace is the best free way to deploy Hermes Agent on HuggingFace Spaces — 2 vCPU, 16GB RAM, 50GB storage, always online, zero cost.

ctrlnode★ 28

Open-source local agent runtime for CTRL NODE — the CLI bridge that pairs your machine with Claude Code, Copilot, Gemini, Cursor and more, and executes tasks from the CTRL NODE dashboard.

plimsoll★ 28

A sandbox service for running untrusted, agent-authored code that reports the isolation boundary each run executed behind. Lessons, no clone needed: https://plimsollmark.github.io/plimsoll/trainers/

agent-sandbox★ 27

Agent — A next-generation sandbox for AI code agents. Environment management, CI/CD pipelines, and multi-agent collaboration.

gen-ai-code-execution-agent★ 27

Secure Dynamic Session Agent for AI generated code execution built using OpenAI, Langchain and Azure Container Apps

shannot★ 27

Human-in-the-loop execution for LLM agents

agentlift★ 27

Deploy agents to Claude Managed Agents, AWS Bedrock AgentCore, and Google. One folder, one definition, one command.

ysa★ 27

"Run AI coding agents (Claude, Mistral, other providers coming soon) in parallel inside hardened, isolated containers with git worktree separation.

kdcube★ 27

Open-source, self-hosted runtime and SDK for AI applications. One tenant/project deployment serves many users and apps with governed tools, scoped credentials, isolated generated code, and cost controls.

claude-code-docker-container★ 27

在網路受限的 Docker Dev Container 裡安全執行 Claude Code,透過 iptables/ipset 防火牆白名單限制 AI Agent 的對外連線,降低資料外洩與誤操作風險。改自 Anthropic 官方 .devcontainer 參考實作。

AgentPod★ 27

Self-hostable, multi-tenant AI agent service with sandboxed code execution(可自托管的多租户 AI Agent 服务,支持沙盒隔离执行)

Aios★ 26

AI-Native Operating Environment — Linux-based OS with Rust kernel modules and Python AI/ML runtime. Local LLMs, multi-agent orchestration, and intent-driven computing, all on-device.

joblet★ 26

Joblet is a micro-container runtime for running Linux jobs with: Process and filesystem isolation (PID namespace, chroot) Fine-grained CPU, memory, and IO throttling (cgroups v2) Secure job execution with mTLS and RBAC Built-in scheduler, SSE log streaming, and multi-core pinning Ideal for: Agentic AI Workloads (Untrusted code)

kocort★ 26

Desktop AI agent runtime with dual-brain safety review, GUI-first operation, local model support, and multi-channel delivery.

PawFlow-Agents★ 26

PawFlow (Platform for Agentic Workflows) Self-hosted agent runtime for real infrastructure. Run durable AI agents against your own files, tools, browsers, desktops, services, and workflows with relay-backed execution, shared context, multi-provider agents, and deterministic flows.

Agent-libOS★ 26

Agent libOS provides a runtime substrate for self-evolving LLM agents with process-like execution, tool management, and security boundaries implemented through explicit capabilities and runtime primitives.

kairos-runtime★ 26

An agent runtime that treats context, execution, and permissions as OS primitives — not LLM problems.

harness-os★ 26

Harness is all you need. The operating system for autonomous AI agents.

agentmux★ 26

The Open-Source Agent Operating Environment Built for Getting Work Done

orpheus★ 25

Orpheus is an Agent Runtime that solves the 'Silent Failure' of CPU autoscaling. It scales on queue depth, persists memory, and recovers from crashes automatically.

python-sandbox★ 25

Secure and lightweight Python code execution environment for LLMs

easl★ 25

Instant hosting for AI agents — turn output into pages worth sharing

agent-runtimes★ 25

🤖 🚀 Agent Runtimes — Managed AI Agents.

screenbox★ 25

Real virtual desktops for AI agents. MCP-native, self-hosted, fully isolated.

retro-agent★ 25

A lightweight AI agent for legacy hardware. Written in Zig, runs on Windows XP SP3 x86 with 64 MB RAM. Connects to Ollama for LLM-powered system diagnostics and management via function calling.

MultiModal-Jupyter-Sandbox★ 25

Simple code sandbox supporting jupyter notebook style code execution. Used for agent training

agent-os★ 25

Local-first AI project OS that turns coding models into reliable software agents with memory, sandboxed execution, verification, recovery, GitOps, and deployment.

nightona★ 25

Open-source continuation of Daytona — secure, elastic sandbox infrastructure for AI code execution and agent workflows. Community fork of the last AGPL-3.0 release (v0.190.0).

awesome-agent-sandbox★ 25

Portable, self-contained sandboxes for AI coding agents - microVMs, containers, isolation harnesses.

sprites-ex★ 25

Elixir SDK for Fly.io Sprites: computers for agents. Manage Sprites and run remote commands from Elixir, with APIs that match the language's conventions.

pier★ 25

Give every agent session its own VM. One command up, zero burn when idle.

boxdown★ 25

CLI for Local Isolated Environments for Coding Agents

microsandbox-reef★ 25

Run OpenClaw, Hermes and your own agents in microsandbox microVMs. One reviewable TOML role sets image, allowed domains and host-bound secrets. No daemon.

neko★ 24

Lightweight AI agent runtime targeting Raspberry Pi Zero 2W and low-end VPS. File-based memory, MCP tool support, Telegram integration — all in a single binary.

rust-bash★ 24

A sandboxed bash interpreter for AI Agents, built in Rust

run402★ 24

Full-stack backend infrastructure for AI agents: Postgres, auth, storage, serverless functions and atomic deploys. TypeScript SDK, CLI and MCP server. Paid with x402/MPP. Open source.

clrk★ 24

Cognitive Loop Runtime for Kubernetes

MonoLight★ 24

MonoLight is a General Autonomous Agent runtime with IM interaction as its primary interaction modality, focusing on safe execution and human-machine collaboration.

branching★ 23

BranchContext gives AI agents and automated workflows copy-on-write branching over filesystems and processes

keyrunner★ 23

Governed API and agent runtime for desktop, VS Code, and CLI. Secure API testing, mocking, automation, secret protection, and controlled AI tool access.

code-airlock★ 23

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everything from your host.

sprites-py★ 23

Python SDK for Fly.io Sprites: computers for agents. Sprite management, remote command execution, filesystems, checkpoints, services, and network policy from Python.

coding-agent-podman★ 23

Run claude with rootless podman

subshell★ 23

An agent / harness multiplexer that allows you to access your agents from any device and machine

omabox★ 23

A hidden Omarchy desktop for your AI agents: they launch, drive and screenshot apps and shell plugins there, never on yours.

pvisor★ 23

Run a coding agent in a staged workspace, review its file changes, and apply only what you keep.

openclaw-control-center★ 22

A cross-device control hub for OpenClaw with guided setup, connector onboarding, mobile pairing, and visible diagnostics.

isolated-function★ 22

A modern solution for running untrusted code in Node.js

bento★ 22

Checkpoint everything git misses in AI agent workspaces. Save, fork, push to any OCI registry.

CachiBot★ 22

The Armored AI Agent — visual dashboard, sandboxed execution, multi-provider LLM support. See what your bots do.

nirdosha★ 22

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation, structured diagnostics, OS-process sandboxing.

picoaide-harness★ 22

PicoAide Harness:企业级 DeepSeek Harness 一体化平台。桌面客户端 + 本地智能体引擎 + 管理后台,支持私有化部署。

ginto.ai★ 21

✅ Agentic OS-aware Intention Programming Technology

claude-podman★ 21

Run claude with rootless podman

sandboxer★ 21

Forkable code execution server for LLMs, agents, and devs

druks★ 21

An operating system for companies: AI agents build and run software tailored to your company. Own your software instead of paying for services you barely use. Agents work in sandboxes, a person approves the important steps, and every run is recorded.

run402-core★ 21

Open-source, self-hostable server and runtime core for Run402 — backend infrastructure for AI agents. Postgres/PostgREST with RLS, storage, routing, functions and portable project archives. Apache-2.0.

case★ 21

Computer for AI Agents

AegisTrace★ 21

AegisTrace - verifiable execution for durable AI agents. Compile policy-bound workflows, record every effect, replay without the network, and prove individual events.

agenticcore★ 20

World's first agentic linux distro.

poke-pc★ 20

safely extend poke's capabilities to your machine with an isolated docker environment. poke pc is a secure mcp worker that lets your ai agent run terminal commands and manage sessions within a sandboxed container

zero★ 20
open-thymos★ 20

AI agent sandbox prison runtime with a local-first desktop app + CLI. Chat with any model (Claude, OpenAI, Groq, Ollama, LM Studio); every action passes Intent → Proposal → Commit through signed capability writs, risk-gated approvals, and a replayable hash-chained ledger. Watch it think in the Mind graph. Cognition proposes; the runtime governs.

jeju★ 20

Declarative, local-first runtime for bounded AI agents — define an agent in one manifest, run it headless, and audit every effect.

ComputerAgent★ 20

Run any AI agent — Claude Code, GAP, LangGraph DeepAgents — in a hermetic sandbox. Reference implementation of the Harness Protocol.

machine★ 20

One isolated Lima VM per GitHub project — sandboxed Claude Code/Codex, Docker, Node, signed git

AGENTCODI★ 20

No Termux required to use AGENTCODI. No WebView shell. No separate gateway setup. with its own native sandbox in protected mode - With its own customized app server.

GocciaScript★ 20

A sandbox-first JavaScript engine for AI agents: host-set capabilities and limits, deterministic runs, TypeScript annotations, test262 on every pull request.

pit★ 20

Give Pi one typed tool instead of a toolbox.

mosaic-companion★ 20

Open desktop runtime for AI agents, tools, and integrations — MCP servers, sandboxed WASM tools, and permissioned add-ons in one workspace.

Hivecrew★ 19

A macOS app for running parallel AI agents in sandboxed local VMs

sdk★ 19

The Agentuity Platform (SDK, tools and runtime)

agenticarch★ 19

User-friendly agentic Linux distribution based on Arch Linux.

loomcycle★ 19

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

hotcell★ 19

Self-hosted sandboxes for AI agents: Docker, Firecracker or Apple Virtualization microVMs. Your real API keys never enter the sandbox. Part of Directionally Local.

More in Agent frameworks & infrastructure