Zero-latency, zero-setup sandbox for AI agents with least-privilege security.
nono is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view nolabs-ai/nono --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 24 days ago.
3696 GitHub stars indicate community interest.
153 open issues signal maintenance load.
Apache-2.0 license detected.
3 security/trust notes recorded.
Setup difficulty is 2/5.
Official NVIDIA-verified skills for AI agents to use CUDA-X libraries and platform tools correctly.
Official Elastic Agent Skills library for AI coding agents to work with Elasticsearch, Kibana, Observability, and Security.
Local GitHub Actions runner for AI agents — test CI/CD workflows locally before pushing.
Open-source LLM app development platform. Build AI workflows, RAG pipelines, and agents with a visual interface.
nono lets you run AI coding agents like Claude Code or Codex in a secure sandbox without any setup. It works instantly, uses no extra disk space, and automatically limits what the agent can access. You can customize and share your own agent configurations.
nono is a Rust-based tool that provides a zero-latency, zero-setup sandbox for AI agents. It supports popular agents like Claude Code, Codex, Pi, CoPilot, Hermes, OpenCode, and OpenClaw on macOS, Linux, and Windows (WSL2). With no daemon, container, or VM, nono enforces a least-privilege sandbox out of the box, ensuring agents only have access to the current directory and nothing else—protecting SSH keys, cloud credentials, and the rest of the filesystem. Users can pull pre-configured profiles from the nono registry, or scaffold and customize their own. The project is built by the team behind Sigstore and emphasizes supply-chain security and zero-trust principles. It also offers a GitHub Action (agent-sign) for secure agent signing. The tool is designed for both individual developers and large organizations looking to operationalize AI agents at scale.
3,696
Stars
245
Forks
153
Issues
Apache-2.0
License
Zero-latency, zero-setup sandbox for AI agents with least-privilege security.
Security-conscious developers, DevOps engineers, AI/ML engineers
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
As with any sandbox, misconfiguration could lead to unintended access; always review profiles. The tool is pre-1.0, so APIs may change; keep an eye on updates.
Similar or complementary options to evaluate include NVIDIA Agent Skills, Elastic Agent Skills, Agent-CI.
Aug 20, 2026