Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 40 of 41
A model router for Claude Code.
A lightweight Python wrapper for Google's Gemini API
Quota-aware Gemini router with persistent usage ledger, native API proxy, TTS and auto-updating CLI
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Chatbot library that calls Groq and Gemini with multi-key automatic failover.
Headroom proxy extension: compress Ollama traffic under its own /ollama route
Hermes provider plugin for the pi-claude-cli Claude worker
Hermes Agent plugin for NanoGPT as model provider.
Python and LangChain client for Kiro's streaming LLM API
Ace Data Cloud chat model and shared LangChain service runtime
LangChain chat model for the AI Stupid Level Smart Router: each request goes to the model that scores best for the task, with your own provider keys.
An integration package connecting Bitdeer AI and LangChain
In-process model routing for LangChain: a chat model that picks one of several candidate chat models per request.
LangChain chat models served through an Otari gateway
LangChain integration for Runcrate: open models behind one OpenAI-compatible API
An integration package connecting TopxAI and LangChain
Tiered team budget enforcement and graceful downgrade for a LiteLLM gateway
Library to easily interface with LLM API providers
Flags LiteLLM proxy settings that cost money or break at scale, like background health checks multiplied across every process
Native Ace Data Cloud LLM integration for LlamaIndex
LlamaIndex LLM for BlockRun: one OpenAI-compatible gateway, paid per call in USDC over x402 on Base or Solana. No API key.
LlamaIndex LLM integration for Runcrate: open models behind one OpenAI-compatible API
AI SDK for Python adapter for llm-catalog: build native `ai` models from a catalog config, routed through your gateway.
LLM plugin for models hosted by FlexAI
LLM clients with a shared model catalog
LLM plugin for the OpenAI Decisions API
A lightweight CLI tool for delegating LLM tasks to expert models across multiple providers.
LLM models from publicai.co
Prove it before you route: test cheaper LLMs on your own traffic and switch only where quality holds.
Send each prompt to the cheapest model that can handle it, and fall back when one fails
LLM plugin for Runcrate: open models behind one OpenAI-compatible API
Run a prompt through the claude CLI or the Anthropic Messages API (direct or via a LiteLLM gateway), with one switch and one result shape.
LLM plugin for models available through TrustedRouter
Reliability for LLM calls: retries with backoff, circuit breakers, rate limiting and multi-provider failover.
Benchmark-driven router for OpenAI-compatible LLM endpoints
Lightweight multi-provider LLM streaming parser with sentence buffering for Voice AI, tag guarding, and streaming tool-call assembly. Zero runtime dependencies.
Unified Python client for chat, embeddings and the Responses API across OpenAI, Azure OpenAI, Azure AI Foundry, Anthropic and Vertex AI, with rate limits, retries, failover, and optional agents with tools.
Call any model with any key, fetched safely from wherever you keep secrets, and see exactly where your money goes
The Mistral Apps gateway seam: the caller token the gateway puts on each request, the middleware that catches it, and the host wiring that makes it the credential a caller's Mistral API calls spend.
Profile-driven async LLM adapter for OpenAI and Anthropic.
OpenAI structured-output provider for the nl2data-core model provider boundary.
Python SDK for Ollama's Decision API. Convert text into structured, typed responses without prose generation using an elegant operator-based DSL.
An integration between the Otari LLM gateway and Haystack
One interface to many LLM providers and models: generation, structured output, embeddings, costs, retries and rate limits.
Google Gemini plugin for PolyLLM.
Official Pura LLM OAuth and delegated inference SDK
Per-request model selection, a feature for pydantic-ai-app-factory
Pydantic AI models served through an Otari gateway
OpenAI for PyFlowRED's AI nodes - and anything that speaks the OpenAI API.
A lightweight wrapper for querying an EC2-hosted LLM via OpenAI API
Haystack integration for Runcrate: open models behind one OpenAI-compatible API
Learns the fixed-choice decisions your LLM makes and answers the ones it is certified on in microseconds, from a small table on your CPU. Zero-code proxy for the OpenAI Decisions API, System One and chat models.
Unified client for multiple LLM providers
LiteLLM's API with Agent Router underneath: the SDK and the local gateway.
LiteLLM's API with Agent Router underneath: the SDK alone, for use with a remote gateway. pip install theagentrouter adds the local gateway.
Agent Router's aigw program, for theagentrouter's local gateway. Installed with pip install theagentrouter.
Lightweight, SDK-free, zero-dependency Python wrapper for chat completions (with streaming) and embeddings across 18 LLM providers behind one normalized surface.
LLM cost routing with correct per-request cost: output-length forecasting, cache-aware tiered pricing, and $/quality ranking.
Per-client budget hard stop and cost logging for LiteLLM proxies, by Tripwire
A ModelProvider for OpenAI-compatible chat and embedding endpoints, proved against the shipped conformance suite
Quiet Core bot - a self-hosted AI agent gateway
Thin Claude Code to NVIDIA NIM translator
Use several Claude subscriptions from one Claude Code setup via a local proxy
LLM plugin for the decision models of the OpenRouter Decisions API
A unified Python client for OpenAI-compatible and multi-provider LLM APIs.
Cloudflare Workers AI and AI Gateway models for Pydantic AI
An AI agent gateway for tool orchestration, automation, and chat integrations.
Provider-neutral LLM service interface for the Hydra harness
`@agentxin-ai/plugin-moonshot` connects [Moonshot AI (Kimi)](https://platform.moonshot.cn/) models to the [AgentXinAI](https://github.com/agentxin-ai/agentxin) platform. The plugin integrates Moonshot's OpenAI-compatible API so AgentXinAI agents can lever
Use multiple ChatGPT Codex OAuth accounts in Pi.
Tinfoil secure OpenAI client wrapper
Use the ChatGPT, Claude, Copilot and OpenCode Go logins in your OpenCode server from any app: an OpenCode V2 plugin serving OpenAI, Anthropic and Gemini compatible APIs.
LightOn TypeScript SDK
Mixedbread AI Provider for running Mixedbread AI models with Vercel AI SDK
Model providers for BanglaClaw: OpenAI-compatible (OpenAI, Ollama, vLLM) and Anthropic
LangChain chat model for Heabsy, an OpenAI-compatible inference API for open models
Zero-config rate limiting, caching, and cost control for LLM calls.
AI addon for CamStack — the `llm` collection provider (cloud, LAN, and camstack-managed local llama.cpp profiles) plus the per-node `llm-runtime` managed executor.
Provider-neutral model-call primitives: usage, pricing, JSON-output adapters, and structured-decision codecs.
Cursor subscriptions (Pro, Pro+, Ultra, Teams) in OpenCode and magpie, through the API cursor-agent talks to
Claude Code API server: OpenAI- and Anthropic-compatible endpoints for Claude Code, using your Claude subscription
Library to easily interface with LLM API providers
LangChain chat model for Obscurify.ai, a private AI API (OpenAI-compatible)
Multi-provider LLM failover with rate-limit handling and automatic retry.
LLM plugin for Obscurify.ai, a private AI API with 200+ models
An LLM request client with its own durable queue: taskiq + Amazon SQS, adaptive limits, retry and fallback.
Local scripted OpenAI emulator: chat/tool loops, SSE, embeddings, models, files and staged uploads without billed inference.
AWS Bedrock Converse provider for Effect AI.
Route sub-tasks to the right model instead of the biggest one: a from-scratch orchestrator with a blackboard, strict JSON contracts and an auditable execution trace.
Keeps an agent answering when its Anyray gateway is unreachable: an httpx2 transport for the OpenAI, Anthropic and LangChain SDKs that resends a call straight to the provider only when the gateway never handled it.
Production-grade, drop-in caching utility for LLM API prompts and responses in Django, cutting token costs and latency.
Bridge remote LLM APIs and SSH over an Apache Guacamole terminal
LangChain integration for Revana: Claude, Gemini, DeepSeek and other chat models through one OpenAI-compatible API key.
A thin, robust HTTP wrapper for the OpenAI, OpenRouter, Anthropic (Claude), and Google APIs (only dependency: httpx)
Gift someone a spending-capped, expiring LLM API key. The tool is published on npm: npx llmgift
rboto: async-only, typed Python client for Amazon Bedrock, powered by Rust. Alpha preview.
rboto: async-only, typed Python client for Amazon Bedrock Runtime, powered by Rust. Alpha preview.
Lightweight LLM connectivity and protocol compatibility tools.