Vertex Ai Python Packages

litellm

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

langchain-google-vertexai

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

langchain-google-genai

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

langchain-google-community

🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)

litellm-proxy-extras

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

litellm-enterprise

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

agentmake

AgentMake AI: a kit for developing agentic AI applications that support 24 AI backends and and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong) Supported backends: anthropic, azure, azure_any, cohere, custom, deepseek, genai, github, github_any, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai

lmux-anthropic

Modular Python library for unified LLM provider access with cost reporting

lmux-azure-foundry

Modular Python library for unified LLM provider access with cost reporting

lmux-aws-bedrock

Modular Python library for unified LLM provider access with cost reporting

lmux-bedrock-shared

Modular Python library for unified LLM provider access with cost reporting

lmux-google

Modular Python library for unified LLM provider access with cost reporting

lmux

Modular Python library for unified LLM provider access with cost reporting

lmux-groq

Modular Python library for unified LLM provider access with cost reporting

lmux-load-balancer

Modular Python library for unified LLM provider access with cost reporting

litellm-dev

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

claudehop-cli

Use several Claude Code accounts on one machine. Move every terminal to another login in one keystroke, or run a different account in each terminal with hop run. One file, no dependencies, no background process. Linux and macOS.

llmstudio

Framework to bring LLM applications to production

lmux-openai

Modular Python library for unified LLM provider access with cost reporting

autollm

Ship RAG based LLM web apps in seconds.

evalforge-lite

Compare text LLMs across OpenRouter, Amazon Bedrock, Google Vertex AI and Microsoft Foundry — bring your own credentials. Automated grading, reports, and an MCP server.

lamia-cloud

Run one-shot, scheduled, or triggered Lamia scripts on Google Cloud. Skip the infrastructure overhead and ship reliable, guaranteed AI workflows.

litellm-core

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

google-cloud-automlops

Build MLOps Pipelines in Minutes