BerriAI/litellm — Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost…

Description and use

BerriAI/litellm: BerriAI/litellm helps turn isolated prompts and tools into repeatable agent workflows.. Use it for coordinate multi-agent workflows; add tool-use pipelines. Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Problem

BerriAI/litellm helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

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]

Source