LiteLLM

public

Open-source AI Gateway and Python SDK giving a single, unified OpenAI-format interface to 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and more). Use it as a Python SDK for direct integration, or deploy the AI Gateway (Proxy Server) as a centralized service with virtual keys, spend tracking, budgets, guardrails, load balancing, and an admin dashboard. MIT-licensed, by BerriAI (YC W23). PyPI: litellm; docs: docs.litellm.ai.

157 nodes240 edgesUpdated 9/2/2026

Connect your agent

Generate a PAT in Account → Access tokens (reuse it on every agent), then drop it into the config below.

One command — a static token, no browser login:

claude mcp add product-graph-public-graphs-by-vibelevel https://graphapi.vibelevel.ai/mcp?workspace=public-graphs-by-vibelevel \
  --transport http --scope user \
  --header "Authorization: Bearer pfg_YOUR_TOKEN_HERE"

Server URL

https://graphapi.vibelevel.ai/mcp?workspace=public-graphs-by-vibelevel