inference-litellm: one OpenAI-compatible model endpoint for every harness, with routing aliases, budgets per run and a spend log, run as LiteLLM with PostgreSQL on Docker.
Cross-referenced across 55 tracked directories
#10421
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
10/24/2026
First Seen
Recently added to the ecosystem
Virag Tripathi <[email protected]>
LangChain integration for CockroachDB with native vector support
Igor Bogdanov
A unified Python connector for multiple LLM providers with YAML-driven configuration.