PHP library for interacting with multiple LLM providers (Google, Mistral, OpenAI, OVH and any OpenAI-compatible endpoint) with failover, retry, and tool calling support
67%
Total Score
caution
Usable with caveats: no commits in three months despite frequent releases.
The repository recorded zero commits and zero active maintainers during the last three months. The frequent release history partly offsets this, but the recent absence of source activity remains a maintenance concern.
Composer build tooling is present, but no security scanning tools were detected. This is a modest transparency and maintenance gap rather than evidence of unsafe code.
The repository has no security policy file, leaving vulnerability reporting and response expectations undocumented.
The single workflow was fully analyzed with no dangerous triggers, untrusted checkouts, or audit findings. However, both of its action references are unpinned, which weakens build reproducibility and supply-chain hygiene.
We didn't find any vulnerabilities for this package.
| Dependency | Last Release | Score |
|---|---|---|
berlioz/helpers Version ^1.13 | — | — |
psr/http-client Version ^1.0 | — | — |
psr/http-message Version ^2.0 | — | — |
berlioz/http-message Version ^2.5 || ^3.0 | — | — |
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.