Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency
Nono is a capability-based, policy-governed sandbox runtime written in Rust that restricts what an AI agent process can access on the host machine, enforcing limits on file paths, network destinations, environment variables, and credentials using kernel primitives (Landlock on Linux, Seatbelt on macOS). It integrates directly with Claude Code via pre-built profiles pulled from a registry, invoked with a single `nono run --profile always-further/claude -- claude` command, and supports other agents including Codex and OpenCode. The core Rust library is policy-free and embeds into any application, with bindings also available for Python, TypeScript, and Go. A standout feature is credential proxy mode, which keeps API keys entirely outside the sandbox rather than injecting them into the agent process, with support for keystore, 1Password, and Apple Passwords. Audit logs, Sigstore-based attestation of instruction files like CLAUDE.md, content-addressable rollback snapshots, and composable policy profiles make the tool particularly relevant for security teams deploying Claude Code in shared or production environments.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/always-further/nono && cp nono/*.md ~/.claude/agents/Subagents overview
What people ask about nono
What is always-further/nono?
+
always-further/nono is subagents for the Claude AI ecosystem. Capability-based agent runtime with fine-grained policies . Brokering access directly within the agent's operating context, with zero setup and zero latency It has 2.7k GitHub stars and was last updated today.
How do I install nono?
+
You can install nono by cloning the repository (https://github.com/always-further/nono) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is always-further/nono safe to use?
+
Our security agent has analyzed always-further/nono and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains always-further/nono?
+
always-further/nono is maintained by always-further. The last recorded GitHub activity is from today, with 171 open issues.
Are there alternatives to nono?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy nono to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/always-further-nono)<a href="https://claudewave.com/repo/always-further-nono"><img src="https://claudewave.com/api/badge/always-further-nono" alt="Featured on ClaudeWave: always-further/nono" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.