Agent frameworks & infrastructure
Agent sandboxes & runtimes
1,721 agents · most starred first
Agent sandboxes & runtimes, page 11 of 18
AI ready linux distribution for agentic development. Optinionated defaults that help me (and possibly you too) get stuff done faster. Installable, Live-Bootable, Customizeable. Built by Finn Glas
OpenClawOS is an OS-like architecture for AI assistants. It provides a kernel-based design with process-isolated applications, enabling reliable multi-channel AI assistant infrastructure.
gradio mcp-server-track code-execution modal sandbox dynamic-dependencies mcp-server region:us
docker region:us
docker openenv rl-environment region:us
EVA - a minimal self-evolving agent that safely rewrites, tests, and promotes better versions of itself inside a hardened Docker sandbox.
Self-healing agent runtime. PCEC engine + Gene Map persistent memory + AMP multi-agent protocol. The operating system for AI agents.
A modular, distributed AI runtime for personal automation, research, and autonomous workflows. Built with Node.js and Python, it connects Android (Termux) edge instances with Proxmox core servers. Features multi-project context memory, a modular tool sandbox, and an organic, trace-based reasoning policy layer.
An event-sourced runtime for AI agents that survives kill -9, written in Rust.
Run Claude Code agents on your own VPS. A web manager spins up sandboxed Docker sessions with Remote Control, a built-in web terminal and GitHub OAuth, backed by Claude, DeepSeek or any Anthropic-compatible model.
A security-conscious, local-first LLM agent in Go powered by Ollama & Model Context Protocol (MCP). Features defense-in-depth sandboxing, tamper-evident audit logging, and MCP tool orchestration.
Hermetic sandbox executor that returns typed, delta-aware feedback to coding agents (Rust). Parsed compiler/sanitizer/test verdicts + run-to-run deltas instead of raw stdout.
Aria — an open-source AI operating system in your browser: a macOS-style web desktop with a live multi-agent brain (local LLM via WebGPU, real tools, live code execution).
Run Claude Code, GitHub Copilot CLI, Antigravity CLI, OpenAI Codex and OpenCode in an isolated Docker sidecar next to your app. The agents get their own headless Chrome and one shared MCP configuration, and each project's logins and history stay inside that project. You can work in VS Code inside the same sandbox.
The scripting language of AI agents: the agent writes it, you review it at a glance, and the program can only do what it declares.
A runtime for AI agents you run on your own Linux machines: kernel-confined, spend-limited, recorded, and driven from Node, the command line or HTTP.
Open-source Rust runtime for autonomous agents — 13 modules, 76 crates, 2625 tests. Event-sourced persistence (Lago), homeostatic regulation (Autonomic), x402 payments (Haima), cryptographic identity (Anima), distributed networking (Spaces), metacognitive evaluation (Nous), OpenTelemetry observability (Vigil).
Deterministic, self-improving AI agent execution harness and runtime for the AXIOM ecosystem. Enforces plan-deterministic execution, parallel swarm orchestration, and signal-level sandboxing.
Enables Autogen agents to securely execute code in isolated remote sandboxes using YepCode’s serverless runtime.
An OS for AI agents: Rust + WASM runtime, typed message bus, event‑sourced memory, and a clean TUI.
Worker examples for stdio Bus kernel - a high-performance message routing daemon for agent protocols.
A data-driven, cryptographically signed, registry-backed AI operating system, with capability-scoped execution and graph-executable workflows — living inside your projects, running through a recursive MCP that goes as deep as you dare.
♜ Deploy OpenClaw AI agents in one click. No credit card, no DevOps, no headaches.
Secure local AI agent runtime — vault-backed secrets, sandboxed execution, cryptographic audit chain, procedural skill system
Sandbox any CLI AI agent so it runs unrestricted without touching your machine. Written in Rust, daemonless, no Docker: each box is a disposable git worktree plus an in-process libcontainer OCI container. Spin up several agents in parallel against one worktree. Built for Claude Code, Aider, Gemini CLI and friends.
A Docker-based isolation harness for running AI coding agents
Launch AI agents in a secure, disposable Linux runtime (Lima or Docker) — with one command.
Private AI workspaces that run locally, using fewer tokens and less compute.
docker region:us
Autonomous agent on ESP32-S3 that rewrites its own Python source at runtime.
ai built in os mainly on rust with some hint of c c++ assembly
Upload a bundle of files and get a shareable web URL. One static Go binary is both the server and the client, built for agents that need to hand a rendered page to a person.
Security-first, brain-agnostic self-hosted agent runtime
Execute SKILL.md agents via 4 modes — binary CLI, npx, HTTP API server, or embedded Node.js SDK
Enterprise Autonomous AI Agent Control Plane & Automation Platform
Aios — Artificially Intelligent Operating System. An AI-native operating environment where no component both decides and executes.
An agentic OS in your browser: the chat is the interface and apps get generated on demand as HTML. Local model via WebGPU, zero install.
Self-hosted deployment for PlanVault — governed AI agent execution runtime. Docker Compose stack, signed images, Cosign verification, single-tenant VPC deployment.
A multi-tenant platform that provisions and routes isolated DeepSeek Harness (dsh) instances — one container per user.
Concept: an operating environment where AI is not an application but the computer's nervous system — organs, afferent perception, a shared scene of state.
C11 agent runtime with a local console, DAG workflows, tool execution, memory and context budgets. Windows / Linux / macOS. 可观测的本地 Agent 运行时。
SKILL.state long-horizon agent-skill runtime for Hermes Agent (arXiv 2608.26263) — explicit-state execution, O(1) prompt, OpenAI-compatible backends
A sandbox fabric for agentic RL in Rust. Containers, microVMs and WASM behind one API, built to create thousands of sandboxes a second across a cluster.
Control plane for a web chat agent to run constrained, auditable jobs on your own machine — GitHub as durable transport, hard capability boundaries, recoverable runs.
An agentic OS in your browser: the chat is the interface and apps get generated on demand as HTML. Local model via WebGPU, zero install.
Research prototype for durable agent execution facts, deterministic acceptance, crash-state inspection, and immutable skill versioning.
Self evolving, Persistent agents for cloud and local workspaces with their own free computers powered by Cloudflare
Headless Windows 11 execution sandbox for AI agents. Typed Rust control plane over KVM/QEMU with an append-only audit journal and strict capability boundary.
gradio region:us
gradio region:us
static region:us
A pure-Go JavaScript runtime for scripts and autonomous AI agents. Agents write and execute JavaScript, use system tools, and delegate work to subagents. Run from the CLI or embed in Go applications.
Run your AI agents anywhere, faster, without managing complex tech.
OCI NodeJS client for Generative Ai Agent Runtime Service
Shennian — AI Agent Control Plane CLI
AI Coder Server - Manages Docker containers for AI agent task execution
AI Agent runtime for Minion - manages status and skill deployment on VPS
Maestro — Autonomous AI agent operating system. Deploy AI employees on dedicated Mac minis.
MakeCoder Coder: AI Agent Runtime OS that runs and orchestrates Claude Code, Codex, Gemini and more across CLI, API, Web and chat
Tuple Agent Runner - Distributed AI agent daemon
AI agent runtime with WebSocket protocol, artifact handling, and secret management
Client SDK for the Tangle Sandbox platform - build AI agent applications with dev containers
AI Agent runtime for CommHub networks. Supports Claude Code CLI, Claude Agent SDK, Codex SDK, Codex app-server, Grok Build ACP, and OpenCode CLI.
CLI for AI agent operating layers and global runtime integrations
NAISYS - Autonomous AI agent runner with built-in context management and cost tracking
The Agent That Lives - daemon-first AI agent runtime
Edgar Allen Code — Headless AI agent execution engine
VESS local AI agent runtime — manages agent identity, permissions, and execution boundaries
AI Agent CLI Security Sandbox for Docker and Podman
CLI for Cogitator AI Agent Runtime
Provider-agnostic managed AI agent runtime for Novu
Agent runtime for the OpenAcme AI agent platform.
Self-hosted AI agent platform — autonomous, multi-channel, multi-model.
AI agent platform — security-first orchestration for autonomous agents
Safe AI-Agent AIEXE Auto
🥩 Meatloaf — AI Agent Sandbox Runtime. Build. Run. Test. Ship.
Runtime SDK injected into sandbox for Agent Tool Protocol
LLMz - An LLM-native Typescript VM built on top of Zui
rvAgent WASM bindings — browser and Node.js agent execution
Secure TypeScript Code Mode for TanStack AI agents to execute sandboxed tool orchestration programs.
Let agents run disposable VMs
Modal Sandbox backend for deepagents
Sandboxed JavaScript REPL for deepagents using QuickJS (WASM)
Virtual File System sandbox backend for deepagents
Daytona Sandbox backend for deepagents
将 AG-UI 兼容的 Agent 部署为 HTTP 服务。
<!-- ~ Copyright (c) 2025-2026 Datalayer, Inc. ~ ~ BSD 3-Clause License -->
Blaxel SDK for TypeScript
An Undici interceptor that routes requests over a worker thread
Stable application runtime and operator control plane for agent workspaces.
AI My API! Typescript sandbox for AI agents to interact with your API in a safe way.
Bridge server that connects Claude Agent SDK and Codex CLI sessions to mobile devices via WebSocket
Agent-first filesystem backed by S3
**An autonomous agent runtime where intelligence is durable, not disposable.**
VeilCLI - Enterprise autonomous agent runtime — local, API-first, multi-model
CLI-first autonomous agent using Subconscious + E2B
Run Claude Code as an autonomous agent in Docker containers with git integration
uAAL — Universal Autonomous Agent Language VM. Stack-based bytecode execution engine for the uAA2++ 7-Phase Protocol.
Run Claude Code as an autonomous agent in Docker & Podman containers
Unstable - PR - Run Claude Code as an autonomous agent in Docker containers with git integration