OpenShell is a safe, private runtime for fleets of autonomous AI agents. Agents are most useful when they can read files, install packages, call APIs, and use credentials. OpenShell gives them that capability without giving them unrestricted access to your data, secrets, or network. You declare what each agent can touch in a policy, and OpenShell enforces it.
OpenShell governs agent behavior in two ways. First, it instruments the kernel to enforce policy on every file access, system call, and network connection at runtime. Each agent runs in an isolated sandbox, and every network connection passes through a policy check before it leaves the sandbox. Agents never see real credentials; OpenShell adds them only to requests bound for approved endpoints. Second, it uses formal verification to check what a policy change would allow before it is applied. Changes that grant risky new access, such as reaching a new host with credentials or calling a new API method, are held for human review.
The 0.1.x series brings a stable release cadence, new isolation primitives, an expanded extension surface, and new APIs. The installer sets up the CLI and a local gateway, and the default sandbox is a minimal Ubuntu image with no agent installed. A guided walkthrough runs the Open Code agent against a free OpenRouter model and shows how to approve new access as the agent needs it.
OpenShell also provides SDKs for Python, TypeScript, Go and Rust, along with installable agent skills for coding assistants. Community support is available through GitHub Discussions and Issues, and security vulnerabilities should be reported under the project's SECURITY.md policy rather than as public issues.
Source: Hacker News · Summarized by HeadlinesBriefing