nono-rs 0.4.1

The Swiss Army knife of agent security

[!WARNING] This is an early alpha release that has not undergone comprehensive security audit We are also in the process of porting the core to its own library. We still welcome PR's, but note a bit of cat herding maybe involved if the change touches a lot of files.

nono is a secure, kernel-enforced capability shell for running AI agents and any POSIX style process. Unlike policy-based sandboxes that intercept and filter operations, nono leverages OS security primitives (Landlock on Linux, Seatbelt on macOS) to create an environment where unauthorized operations are structurally impossible.

nono also provides protections against destructive commands (rm -rf ..) and provides a way to securely store API keys, tokens, secrets that are injected securely into the process at run time.

[!NOTE] NEWS! Work is underway to seperate the core functionality into a library with C bindings, which will allow other projects to integrate nono's security primitives directly without shelling out to the CLI. This will also allow us to expand support to other platforms like Windows. Initial languages will be Python, Typescript, and of course Rust. Following up with Go, Java, and C# bindings.

Many more features are planned, see the Roadmap below.

Quick Start

MacOS

brew tap always-further/nono 
brew install nono

[!NOTE] The package is not in homebrew official yet, give us a star to help raise our profile for when request approval

Linux Package Managers

We are in the process of packaging nono for popular Linux distributions. In the meantime, you can use the prebuilt binaries or build from source.

Building from Source

See the Development Guide for instructions on building nono from source.

Use of AI for Development

We encourage using AI tools to contribute to nono! However, you must understand and carefully review any AI-generated code before submitting. AI is a part of the life of software development now, but its use can unwittingly introduce security vulnerabilities — and the security of nono is paramount. Always review and test your code thoroughly, especially around core sandboxing functionality. Being able to explain your changes in your own words also helps reviewers. If you don't understand how a change works, please ask for help in the Discord before submitting a PR.

Supported Clients

nono ships with built-in profiles for popular AI coding agents. Each profile defines audited, minimal permissions so you can get started with a single command.

Don't see your tool? nono is agent-agnostic and works with any CLI command:

nono run --allow . -- my-agent

Projects using nono

Shell Alias (Claude Code example)

For quick access, add a shell function:

sclaude() {
    nono run --profile claude-code --allow . "$@" -- claude
}

Usage:

sclaude                           # Current directory only
sclaude --allow /tmp              # Current directory + /tmp
sclaude --read ~/Documents        # Current directory + read-only ~/Documents

Features

• No escape hatch - Once inside nono, there is no mechanism to bypass restrictions
• Agent agnostic - Works with any AI agent (Claude, GPT, opencode, openclaw) or any process
• OS-level enforcement - Kernel denies unauthorized operations
• Destructive command blocking - Blocks dangerous commands like rm, dd, chmod by default
• Cross-platform - Linux (Landlock) and macOS (Seatbelt)

Usage

# Allow read+write to current directory
nono run --allow . -- command

# Separate read and write permissions
nono run --read ./src --write ./output -- cargo build

# Multiple paths
nono run --allow ./project-a --allow ./project-b -- command

# Block network access
nono run --allow . --net-block -- command

# Dry run (show what would be sandboxed)
nono run --allow . --dry-run -- command

# Start an interactive shell inside the sandbox
nono shell --allow .

# Check why a path would be blocked
nono why --path ~/.ssh/id_rsa --op read

Command Blocking

nono blocks what might be considered dangerous commands by default to prevent AI agents from accidentally (or maliciously) causing harm. This provides defense-in-depth beyond filesystem restrictions.

Blocked Commands

The following categories of commands are blocked by default:

Overriding Command Blocks

# Allow a specific blocked command (use with caution)
nono run --allow . --allow-command rm -- rm ./temp-file.txt

# Block an additional command
nono run --allow . --block-command my-dangerous-tool -- my-script.sh

Kernel-Level Protection

nono applies kernel-level protections that limit destructive operations:

• File deletion blocked outside granted paths - unlink/rmdir syscalls are blocked for system paths like /tmp, /dev, and any path not explicitly granted with --allow or --write
• Directory deletion blocked everywhere - rmdir is blocked even within granted write paths (Linux: RemoveDir excluded from Landlock rules; macOS: global deny file-write-unlink with targeted overrides for file deletion only)

Within paths you explicitly grant write access to (--allow or --write), file creation, modification, and deletion are permitted - this is necessary for normal file operations like atomic writes.

# File deletion blocked in system paths (even with --allow-command rm)
$ nono run --allow ./project --allow-command rm -- rm /etc/hosts
rm: /etc/hosts: Operation not permitted

Platform Support

Roadmap

Planned Features

Security Model

nono follows a capability-based security model with defense-in-depth:

1. Command validation - Dangerous commands (rm, dd, chmod, etc.) are blocked before execution
2. Sandbox applied - OS-level restrictions are applied (irreversible)
3. Kernel enforcement - Directory deletion blocked everywhere; file deletion blocked outside granted write paths
4. Command executed - The command runs with only granted capabilities
5. All children inherit - Subprocesses also run under restrictions
6. Key isolation - Secrets are injected securely and cannot be accessed outside the sandbox

Documentation

Full documentation is available at docs.nono.sh, including guides for supported clients, configuration, and building from source.

Security

If you discover a security vulnerability, please do not open a public issue. Public disclosure of vulnerabilities can put all users at risk. Instead, please follow the responsible disclosure process outlined in our Security Policy.

License

Apache-2.0