litellm
44,383Call any LLM using the OpenAI API format — proxy server and Python SDK.
PreventionIn-generationFully autonomousStableTier 2AEnvironment
Maturity tier details
Computed tier: 2A(raw score 4.86). Effective tier: 2A.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.86
Source of truth:pipeline/maturity/score.py
Description
LiteLLM is an LLM proxy + Python SDK that exposes 100+ model providers behind the OpenAI API. Functions as an enterprise gateway with virtual keys, spend tracking, failover, and rate limits. De-facto standard for provider-agnostic LLM access.
Why it's included
Multi-provider gateway cell — canonical point of comparison for bifrost and manifest.
Addresses failure modes
- Scope creep — Actions outside declared task boundary.
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
Techniques
provider-shimvirtual-keysspend-trackingfailover