Litellm Python Packages

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]

strands-agents

A model-driven approach to building AI agents in just a few lines of code.

strands-agents-tools

A set of tools that gives agents powerful capabilities.

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]

langchain-litellm

🦜🔗 LangChain interface to LiteLLM

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]

strands-agents-builder

An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder can help you to build your own agents and tools.

strands-agents-mcp-server

This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite AI coding assistant to vibe-code Strands Agents.

claude-code-llm-router

DEPRECATED: Use 'llm-routing' instead. This package provides redirect to the new package.

agentpool

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).

llm-routing

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain keeps costs 70–85% lower.

rigging

Lightweight LLM Interaction Framework

cloakllm

Python SDK — PII cloaking middleware for LLM calls (spaCy NER + regex + Ollama)

llmling-agent

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).

terradev-cli

NUMA-aware GPU provisioning and orchestration for stateless MoE workloads of all sizes

agenticore

Two modes, one binary — a fleet orchestrator that clones repos and ships PRs via Claude Code, OR a drop-in OpenAI-compatible chat completion endpoint for customized Claude agents with real-time token-by-token thinking + tool-call streaming. LibreChat/OpenWebUI/LiteLLM-ready. Helm + KEDA + OTEL.

fast-litellm

High-performance Rust acceleration for LiteLLM - providing significant performance improvements for connection pooling, rate limiting, and memory-intensive workloads.

a2a-handler

A2A Protocol client and developer toolkit.

blockrun-litellm

LiteLLM adapter for BlockRun — call x402-paid AI models through LiteLLM (custom provider or local OpenAI-compatible proxy)

llmgate

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

cnllm

中文大模型通用SDK，系统性优化接口适配、增强响应解析和批量处理等能力，深度适配 OpenAI 生态内 LangChain、LlamaIndex、AutoGen 等大模型应用框架。支持作为Agent Skill部署到各种AI编程工具。

apex-ai

Production-grade terminal AI coding agent with 85+ models support, multi-agent system, and rich terminal UI. Built in Gabon 🇬🇦 for the world.

code2logic

Code2Logic - Source code to logical representation converter for LLM analysis, featuring Tree-sitter parsing, dependency graph analysis, and multi-language support.

kodeagent

The minimal AI agent engine