# Berri AI | Knowledge Base | Instagit

The fastest way to take your LLM app to production

---

## Repositories

### [litellm](/BerriAI/litellm)

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

- 23 articles | 40.8k stars
- Tags: deep-dive, performance, how-to-guide, architecture, best-practices, migration-guide