nono
5,067Capability-based sandbox for securely running AI agents with zero setup
Activity band details
Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.
Computed band: D
(raw score 4.48).
Shown band: D
.
Facets:
documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_push=2stars=1.48
Source of truth: pipeline/maturity/score.py
Description
nono is a capability-based, multiplexing sandbox tool designed for developers to securely run AI agents. It provides zero-setup security isolation enabling a seamless path from development to production without additional infrastructure or latency overhead.
Why it's included
Occupies prevention × in_generation × fully_autonomous as a capability-based sandbox that mediates an agent's syscalls while it is still acting, rather than isolating a whole job at the container boundary (contrast modal, e2b, daytona, which sit in recovery × post_generation). The novel primitive is zero-setup multiplexed capability enforcement so a single host can safely run many concurrent agent sessions without per-agent VM provisioning, useful as the local-dev-mode exemplar of in-generation environment control.
Addresses failure modes
These tags are the catalog's claim about what nono is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured nono, so none of these tags is tested here.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
- Scope creep — Actions outside declared task boundary.
- Supply-chain attack — Slopsquatting, typosquatting, compromised MCP servers.