Strands Box
Sandbox your AI agent: default-deny rules for what it can run, read, write and reach.
About Strands Box
Strands Box is an open-source sandbox engine for AI agents. It runs any agent program inside OS-level isolation, then checks its shell commands, Python code, outbound network requests and MCP tool calls against policies written in Dogwood. Anything the policy engine checks is denied unless a rule permits it.
Why it matters: the rules can depend on what the agent already did. A file read through the shell can make the gateway refuse a later outbound HTTP request, which is the exfiltration pattern you actually worry about. The gateway also injects API credentials into permitted requests, so the agent never holds the secrets.
Written in Rust, Apache-2.0, about 390 stars at the time of listing. Still a preview: macOS on Apple silicon only for now, with Linux planned.
The facts
- Type
- Github
- Tags
- AIDeveloper Tools
- Listed
- October 13, 2026
More Github
See all →- GrandetCompare listed API prices for any model, then let your agent connect the cheapest one.
- muA coding agent that hands its yes/no calls to a small, fast judge model at 40 decision points.
- pagesiftOne self-hosted Rust binary that turns web pages, PDFs and Office files into Markdown for agents.
- Coder EvalPlaywright for coding agents: test that your skills and MCP servers work when an agent uses them.
- EvalForgeTurn promptfoo, Ragas or DeepEval results into CI gates that fail the build when quality regresses.