Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 21 of 41
llmserver_call
A wrapper for OpenAI utilities
A minimal, generic client for AI models (OpenAI, Anthropic, Google, xAI) with middleware support.
An extension for using Gemini with aiconfig
An extension for using the Groq client wrapper with AIConfig.
Model Parser extension for Llama
Package implementing adapter from DIAL Chat Completions API to Anthropic API
Python βιβλιοθήκη για επικοινωνία με το OpenAI API μέσω requests
AWS boto3 bedrock client in async
An unofficial API for Claude AI, allowing users to access and interact with Claude AII
An asyncio wrapper for the OpenAI ChatGPT API
Anthropic provider for Airbender Python SDK
OpenAI provider for Airbender Python SDK
Enterprise LLM proxy built on LiteLLM — logging, guardrails, and unified access for AI coding tools.
A Python library for interacting with Pollinations.ai API with support for text, images, and audio processing.
ALEA LLM client abstraction library for Python
A unified interface for querying Large Language Models (LLMs) across multiple providers using LiteLLM and OpenRouter
langchain-openai package for ally
llamaindex azure openai package for ally
Bridge Anthropic API to OpenRouter and OpenAI models.
Drop-in replacement for the Anthropic SDK that silently handles Claude 4.6 breaking changes
The official Python library for the anthropic API
Add your description here
Decrypt provider API keys using X25519 sealed box encryption and challenge-response authentication
A thin, unified LLM abstraction layer. Call any LLM with a single API.
The GPT-4 API is an interface for interacting with the powerful GPT-4 language model. It allows you to generate natural language text, perform question-answering tasks, and more. Whether you're building chatbots, content generators, or creative writing tools, GPT-4 has got you covered!
Create a Python package.
All in one AIGC API package for Python
A package for interacting with the APIMyLlama API
Unified LLM abstraction layer for autonomous agents
The arc connecting you to every LLM. Minimal dependencies, maximum performance.
Shared helper for calling LLM providers across the ARP/JARVIS stack.
A Python utility to query Amazon Bedrock
Renamed to llm-minder. Installs llm-minder and keeps `import async_batch_llm` working as an alias.
Async OpenAI API wrapper - [Incomplete]
async client for claude.ai and slack.com
An asynchronous handler for multiple LLM APIs
Unofficial Async Python client library for the OpenAI API
Python SDK for Aura LLM Gateway - Open Responses API
Async Python client for Autobyteus LLM API
AutoGemini - 流式Gemini API处理系统
Gigachat client for autogen
An OpenAI-compatible API server for AutoGen.
This is an autogen>=0.4 extension for integrating external models through the OpenAI API.
Library for Mixing Multiple Models with differential costs and performance.
AI agent wrapper for AvalAI API with retry and model fallback support
A unified wrapper for multiple LLM APIs including OpenAI, Gemini, and Anthropic
Make the Amazon Bedrock Runtime API easier to use with intuitive Python interfaces and type-safe utilities.
A lightweight library for generating short-term bearer tokens for AWS Bedrock API authentication
Async Python wrapper for AWS Bedrock LLMs with caching, retries, and structured outputs
Python client sdk of CR-LLM.
Anthropic Claude transport for Axio (direct API and Vertex AI)
OpenAI-compatible transport for Axio
AxonFlow governance integration for LiteLLM
A Python package that provides an easier user interface for multiple LLM providers.
Azure OpenAI client wrapper with rate limiting, cost tracking, and retry logic
High-throughput scheduler & resilience toolkit for Azure OpenAI endpoints (queueing, rate-limit smoothing, backoff, tracing).
Static token limits for Azure OpenAI models (context/output), with CLI.
ChatGPT is a reverse engineering of Azure ChatGPT API
A version of the OpenAI package that allows the caching of responses, tailored for the CBS BA class.
llama-index llms azure openai integration
llama-index llms bedrock converse integration
llama-index llms openai integration
llama-index program openai integration
One client to rule them all
An abstraction layer for AWS Bedrock. Removes the need to keep track of response/request schemas.
A developer-friendly helper for OpenAI's Batch API
Async batch runner for OpenAI API calls with streaming support
Easy calling chatgpt with batched instances
like itertools.batched but for calling LLM
Client library for the anthropic API with the AWS Bedrock endpoint.
Python SDK for AWS Bedrock Converse API with tool calling, embeddings, and vector search
Python client for AWS Bedrock Gateway with IAM authentication
Login into your AWS and call Bedrock models in Python
Small, opinionated AWS Bedrock client wrapper: adaptive throttle, cache-aware cost tracking, and structured-output parse-and-repair. Single-cloud, single-purpose.
Drop-in replacement for boto3 bedrock-runtime client with token limiting
Production-grade boto3 toolkit for AWS Bedrock: typed retry, per-model timeouts, capability lookup, full token usage with cache fields, PII-safe Guardrails.
AWS Bedrock region load balancer with round-robin distribution and batch processing
Python SDK and CLI for BedrockRouter — use every AWS Bedrock model through a self-hosted proxy with friendly aliases and cost tracking
A comprehensive Python library for managing AWS Bedrock Converse API interactions with multi-model support, intelligent retry logic, and parallel processing capabilities
LiteLLM adapter for BlockRun — call 90+ AI models via LiteLLM with a BlockRun API key or an x402 USDC wallet (Solana or Base)
Bohilib plugin for Cohere by bodhiext
Bodhilib plugin for OpenAI APIs
Universal LLM client with API key rotation, rate limit management, and custom fallback strategies. Drop-in OpenAI SDK replacement with optional LangChain support.
A wrapper for litellm with TAIDE configuration support
Provider-agnostic LLM client with agentic capabilities. One interface, any provider.
OpenAI adapters for Bridgic.
OpenAI-like LLM adapters for Bridgic, enabling connectivity with external LLM providers.
A free and open source API for accessing various large language models
This is a reserved placeholder package to mitigate dependency confusion risks.
A version of the OpenAI package that allows the caching of responses
Auto-optimize LLM prompt caching. Save 60-90% on Claude, GPT & Gemini API costs.
Asynchronous, concurrent requests to the LLM REST APIs.
Keep callm and process thousands of requests without (rate) limits.
一个简单的低负载联网网关,提供HTTP请求路由和处理功能