PyPI Stats

Search Packages

Find Python packages by name, description, GitHub topic, or filter by metrics
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]

346.9M 46K 8K
BerriAI
litellm-proxy-extras

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]

1.5M 46K 8K
BerriAI
litellm-enterprise

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]

1.3M 46K 8K
Portkey-AI
portkey-ai

Build reliable, secure, and production-ready AI apps easily.

586K 112 30
AI-Stats
ai-stats-py-sdk

Open-source, OpenAI-compatible AI gateway with health-aware routing, failover, and live telemetry (cost, latency, errors). Built for production.

3K 4 3
geeks-accelerator
ollama-herd

Local AI load balancer for Ollama fleets — auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.

3K 7 0
Hypothesize-Tech
cost-katana

Cost Katana Python

2K 0 0
MichaelAdamGroberman
freemygpt

FreeMyGPT — HTTP gateway that lets ChatGPT (and any LLM) drive any local MCP server via simple GET requests. Hybrid: MCP stdio backends by default, Codex CLI and other runtimes via bundled adapters.

1K 1 0
Kenza-AI
sagify

LLMs and Machine Learning done easily

1K 442 68
smigolsmigol
llmkit-sdk

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

1K 10 3
Portkey-AI
rubeus

Build reliable, secure, and production-ready AI apps easily.

827 112 30
Tanantor
langgate

Lightweight AI inference gateway - local model registry & parameter transformer (Python SDK) - with optional Envoy proxy processor and FastAPI registry server deployment options.

725 6 0
vllm-project
vllm-sr-sim

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

673 4K 654
wso2
amp-instrumentation

WSO2 AI Agent Manager is an open control plane designed for enterprises to deploy, manage, and govern AI agents at scale.

562 37 27
schmitech
schmitech-orbit-client

The self-hosted AI gateway for production RAG across LLMs, databases, APIs, and files.

513 253 43
adwantg
kvfleet

Production-grade, KV-cache-aware intelligent routing for self-hosted and hybrid LLM fleets.

464 0 0
ferro-labs
ferrolabsai

Official Python SDK for Ferro Labs AI Gateway — route LLM requests across 29 providers with a single OpenAI-compatible API

455 1 0
pouriamrt
fastapi-ai-router

FastAPI middleware that turns your existing routes into a natural-language-callable surface using LLM function-calling. Drop-in. Zero new metadata.

433 1 0
shin-bot-litellm
litellm-mcp

MCP server giving AI agents access to 100+ LLMs through LiteLLM

388 38K 6K
monkdbofficial
mcp-monkdb

An MCP server 🚀 for MonkDB, licensed under Apache 2.0 📜

365 2 1
gravtice
nous-genai

Single-endpoint GenAI SDK (multi-provider, multimodal)

191 1 0
gravtice
genai-calling

Single-endpoint GenAI SDK (multi-provider, multimodal)

190 1 0
BerriAI
litellm-ad

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]

142 46K 8K
hyperion-hq
hyperion-ai

The official Python SDK for the Hyperion AI Gateway

134 14 3