always-further/nono

Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with secure key management, atomic rollback, cryptographic immutable audit chain of provenance. Run your agents in a zero-trust environment.

60
/ 100
Established

This tool helps developers and AI engineers safely run AI agents and automated processes. It takes any AI agent as input and creates a secure, isolated environment around it, producing a protected execution of your agent with verifiable audit trails. This is for anyone deploying or experimenting with AI agents and wanting to prevent unauthorized access or actions.

980 stars. Actively maintained with 325 commits in the last 30 days.

Use this if you need to run AI agents or scripts in a highly secure, restricted environment to prevent them from accessing sensitive data or performing unintended actions.

Not ideal if you are looking for a general-purpose containerization solution or if your primary concern is performance over absolute security isolation.

AI Agent Security Secure AI Deployment Zero-Trust AI Agent Sandboxing AI Governance
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 17 / 25

How are scores calculated?

Stars

980

Forks

73

Language

Rust

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

325

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/always-further/nono"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.