PyPI Stats
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About
Home

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
llimona-org
llimona

Llimona is an open and modular Python framework for building production-ready LLM gateways

16K 1 0
Oaklight
llm-rosetta

Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome!

6K 20 1
thatAverageGuy
llmgate

Lightweight, provider-agnostic Python LLM library — one API for OpenAI, Gemini, Anthropic, Groq, Mistral, Cohere, Azure, Bedrock & Ollama. Vision, streaming, tools, batch.

3K 2 0
Nayjest
lm-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

2K 115 12
Nayjest
ai-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

2K 115 12
doramirdor
nadirclaw

Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

2K 447 56
Nayjest
llm-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

1K 115 12
Nayjest
inference-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

1K 115 12
Nayjest
openai-http-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

1K 115 12
Nayjest
lm-proxy-server

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

1K 115 12
Nayjest
oai-proxy

OpenAI-compatible HTTP LLM proxy / gateway for multi-provider inference (Google, Anthropic, OpenAI, PyTorch). Lightweight, extensible Python/FastAPI—use as library or standalone service.

982 115 12
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
kesiee
llmgt

Plug-and-play LLM connector via YAML config — 21 providers, async, tool calling, structured outputs, embeddings, middleware. Zero bloat.

665 3 0
adwantg
kvfleet

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

464 0 0
shin-bot-litellm
litellm-mcp

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

388 38K 6K
yangfei222666-9
taijios-soul

Archived TaijiOS legacy prototype; current main repo is yangfei222666-9/taiji.

329 0 0
kikuai-lab
reliapi-sdk

Small reliability layer for HTTP APIs and LLM calls. Idempotent HTTP/LLM proxy with retries, cache, circuit breaker and predictable AI costs.

273 8 0
ruslanmv
ollabridge

Turn your PC into a private, OpenAI-compatible LLM provider in ~60 seconds

220 0 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
BerriAI
litellm-plus

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]

97 46K 8K
    • Data from PyPI, GitHub, ClickHouse, and BigQuery