Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
78%
Total Score
healthy
Healthy: frequent releases and current repository activity outweigh concentrated maintenance and workflow-hygiene concerns.
The package runs postinstall and prepare scripts, which can perform installation-time work and increase dependency-install complexity, although this is consistent with a package that supplies native bindings.
One contributor made all 15 commits in the last 3 months, creating a concentrated maintenance risk; organization backing provides some capacity for handoff but does not demonstrate a second active contributor.
The repository uses TypeScript, Vitest, CMake, Vite, and npm scripts, but no security-scanning tools were detected, leaving a modest transparency gap.
No SECURITY.md or other security policy was detected, making vulnerability-reporting expectations unclear.
All three workflows were analyzed without failed files, and the pull_request_target workflow has no untrusted checkout or script-injection sink. However, all 51 action references are unpinned, and the high-confidence low-severity adhoc-packages finding indicates a workflow installs outside a lockfile.
We didn't find any vulnerabilities for this package.
| Dependency | Last Release | Score |
|---|---|---|
ora Version ^9.3.0 | — | — |
bytes Version ^3.1.2 | — | — |
chalk Version ^5.6.2 | — | — |
ipull Version ^3.9.5 | — | — |
which Version ^6.0.1 | — | — |
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.

I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001Compliant
ISO 42001Compliant© All Intel data is openly available and commercially licensed.