sandbox.
Everything we've published on sandbox across guides, agents, hardware reviews and glossary entries: 17 entries in total.
Guides (1)
- Self-hosted AI security best practices: a playbookAI Agents · 2026-10-18
Securing an AI agent you host yourself: threat model, sandbox tiers, where credentials belong, Tailscale or SSH instead of a public port, logging, incident response.
Agents (7)
- OpenClaw
Self-hosted AI agent at the centre of the January 2026 security crisis. Its tool sandbox is off by default: the main session's tools run on the host until you configure one.
- Hermes Agent
Agent from Nous Research (MIT, Python). Runs shell commands on the host by default, with an approval step for dangerous ones; Docker and cloud sandboxes are options. Works with many LLM providers.
- Nanobot
Personal AI agent in Python (MIT) with a browser UI and chat apps. Native Anthropic, OpenAI and OpenRouter providers plus local servers; its shell sandbox is off until you switch it on.
- NanoClaw
Small TypeScript agent (MIT) built on Anthropic's Claude Agent SDK. Every agent runs in its own Docker container, on macOS, Linux or Windows through WSL2.
- IronClaw
Rust agent from NEAR AI, MIT or Apache-2.0. Untrusted tools run in a WebAssembly sandbox with declared capabilities, and secrets are injected outside them.
- ZeroClaw
Single Rust binary from ZeroClaw Labs, MIT or Apache-2.0. Works with Anthropic, OpenAI, Ollama and about twenty other providers, and turns on an OS sandbox it detects.
- Moltworker
Cloudflare's experimental package that runs OpenClaw inside a Cloudflare Sandbox container behind a Worker. Needs the Workers Paid plan.
Hardware (1)
- Mac Mini M4 / M4 Pro
Mac mini M4 and M4 Pro for local LLMs: 16 to 64 GB of unified memory at 120 or 273 GB/s, the two specs that decide which models load and how fast.
Glossary (8)
- Hermes Agent :Open-source (MIT) AI agent from Nous Research. Multi-LLM; runs commands on the host behind approvals unless you choose a sandbox backend.
- IronClaw :Rust agent from NEAR AI, MIT or Apache-2.0, that runs untrusted tools in a WebAssembly sandbox and keeps secrets out of their reach.
- ZeroClaw :Single-binary Rust agent runtime, MIT or Apache-2.0, with approvals and an OS sandbox on by default and pluggable model providers.
- Moltworker :Cloudflare's experimental package that runs OpenClaw in a Cloudflare Sandbox container behind a Worker.
- Sandbox :Isolation layer that constrains what an agent's tool execution can access on the host.
- Docker sandbox :Sandbox using a Docker container with filesystem mount and network policy controls.
- gVisor :User-space kernel that runs as a sandbox layer between containers and the host kernel.
- Sandboxed tool execution :Running an agent's tool calls inside an isolated environment that limits filesystem, network and process access.