Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 36 of 41
HiperRouter CLI - Start and manage HiperRouter AI Agent & Server
Cost-optimal model router for AI agent harnesses — route each query to the cheapest model that's good enough (k-NN over labelled embeddings). The productized DRACO Phase-2 finding.
LLM capture proxy with Anthropic cache_control TTL stamping, vision handoff, concurrency gating, rate limiting, and a live inspection dashboard
Local AI gateway for OpenCode with tool/function calling — use any model via OpenAI, Anthropic, or Gemini API format
Тонкий шар роботи з LLM (локальні omlx + хмарні провайдери) поверх pi: model tiers, one-shot, agentic-раннери, write-guard, trace, telemetry, prompt-budget
Rulvar first-class provider adapter over @anthropic-ai/sdk.
Rulvar bridge adapter wrapping any Vercel AI SDK LanguageModelV4 as a ProviderAdapter.
Gateway Agnostic SDK for Punk's hosted AI gateway: OpenAI, Anthropic, OpenRouter, Vercel AI SDK, LangChain, agent tracing, tool caching, and governance.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Drop-in OpenAI-shaped client for Cursor models (LangChain / LangGraph optional). Pass apiKey + model.
TypeScript Fastify AI protocol gateway for OpenAI, Anthropic, Gemini, MCP and agent workflows.
Free OpenAI API access with your ChatGPT account.
9Router v2 — Monorepo (frontend + backend)
OpenAI-compatible API gateway for Grok CLI — with Admin panel, safe mode, and gctoac CLI
OpenAI-compatible language model adapter for Pilot (Ollama, OpenAI, OpenRouter, and similar endpoints).
Bridge Claude Code to OpenAI and OpenCode Go models — API keys or ChatGPT/Codex-plan OAuth, with prompt caching, auto-compaction, model switching, and a Claude Code binary patcher
OpenAI Codex provider for AgentLayer and the AI SDK. It talks to the ChatGPT Codex responses endpoint (`https://chatgpt.com/backend-api/codex/responses`) and supports ChatGPT OAuth/API-key auth through `@humanlayer/agentlayer-provider-auth`. Every factory
Local Anthropic API powered by your Claude Max subscription. One subscription, every agent.
OpenAI-compatible streaming model provider for Truss.
Core auth and in-memory OpenAI-compatible transport for openai-oauth.
Responses-compatible API bridge for Cursor Agent CLI
OpenAI-compatible dynamic LLM router — a single Go binary, installed via npm as a prebuilt native binary
Pi extension that syncs models from an OpenAI-compatible API and enriches them with pricing and capability metadata.
Unified LLM provider SDK for HoloScript - OpenAI, Anthropic, Gemini, OpenRouter, xAI, and local LLM adapters
OpenCode plugin for auto-discovery of OpenAI-compatible models with dynamic provider configuration
Autumn usage tracking adapters for AI SDKs and gateways (Vercel AI SDK, OpenRouter)
Config-driven SDK for selecting, extending, and instantiating LLM providers and models
Standalone OpenAI-compatible LLM gateway — multi-provider proxy with pluggable inference metering
AgensFlow adapter for LangGraph — decorator-based routing across a declared model pool
A local zero-token agent status API with OpenAI and Anthropic compatible streaming
Protocol bridge for OpenAI Responses, Chat Completions, and Anthropic Messages clients.
LLM response cache for AgenticStack: provider wrapper with in-memory LRU and SQLite backends
A local OpenAI-compatible proxy that reduces agent context waste and proves behavior held.
Reserved namespace placeholder. The real brink-litellm-plugin is not yet public — see README.
LLM Pipeline Query Optimizer — automatic model routing, cost optimization, and quality-aware escalation.
Experimental subject-scoped ChatGPT OAuth and subscription transport
An LLM client with cache and type checking
Use Eden AI with Haystack to build AI applications with 500+ AI models through one unified, OpenAI-compatible API.
Unofficial OpenAI-compatible HTTP bridge for Factory Droid
A functionnal oriented Python CLI for LLM calling with multi provider and multi model
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
A proxy service converts ModelScope and SiliconFlow image APIs to OpenAI-compatible format
Drop-in ChatAnthropic replacement backed by the Claude Code CLI — use your Claude Pro/Max subscription, no API key needed
LiteLLM / OpenAI-compatible gateway doctor CLI (ping, tokens, context bench)
Custom LiteLLM providers for Pollinations.ai and AI Horde, two free image-generation APIs
Pareto-optimal OpenRouter provider chooser for LiteLLM
Local proof harness for LiteLLM context-window routing
Universal LLM API client for 174 providers — chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
llama-index llms iflytek spark integration
A resilient multi-provider LLM layer that automatically fails over to alternative models and providers when requests fail.
Cross-vendor LLM quota / budget self-check CLI. Stable 0/1/2/3 exit-code contract lets any AI agent gate its work before burning through budget. Supports MiniMax Token Plan, OpenRouter credits, self-hosted LiteLLM proxy spend, and self-logged JSONL (any LLM vendor).
Free-first LLM routing for Python: local Ollama -> OpenRouter free models -> paid Anthropic API, with automatic fallback and a savings ledger.
Model names, pricing, and free-tier metadata for OpenAI, Anthropic, and Google Gemini.
LLM plugin to serve an OpenAI Chat Completions API endpoint
A tiny, readable circuit breaker for LLM calls: hard budget caps that fail over to a free local model instead of raising or overspending.
Composable pre-call and post-call hooks for LLM API calls: pricing, budgets, cost caps, rate limits, event log, observability.
LLM plugin for the Meta AI API
Perplexity's Agent API as a model for Simon Willison's llm CLI.
Resilient cascading LLM inference across multiple providers with failover, circuit breaking, and retry cooldowns
Client-side rate limiting for the Claude API. Never sees your API key.
Cost-aware, latency-optimized routing for multiple LLM API providers
LLM plugin for models hosted by UnoRouter
Async LLM router across AWS Bedrock, Google Gemini, and Groq providers
LLM plugin for Z.AI / GLM models with Coding Plan support
LLM plugin for Z.AI / GLM models with Coding Plan support
LLM plugin for ZenMux.ai - OpenAI Chat Completions + Anthropic Messages API
A lightweight Python decorator for caching, rate limiting, and retrying LLM API calls.
Intelligent routing, load balancing, and failover for LLM providers
A production-ready routing, fallback, and rate-limiting client for OpenAI-compatible LLM endpoints.
Shared AWS Bedrock internals (SigV4 signing, event-stream decoding, Anthropic pricing) for lmux
Use the OpenAI Python SDK with your own ChatGPT subscription
ChatGPT-5.4 Nano 中转服务 SDK - 每天免费 1.0K tokens,国内开箱即用
Neutral LLM gateway: typed contracts, provider adapters and explicit retry, fallback, usage and cost accounting.
Normalize OpenAI-compatible API failures, plan conservative retries, redact logs, and inspect SSE streams
Streaming, multi-provider LLM bridge + markdown rendering toolkit for terminal apps.
Client helper for ProxyLLM, the OpenAI-compatible LLM gateway: one-line OpenAI client wiring plus the autonomous email-OTP account signup flow.
A personal AI model-routing stack that learns from your usage
Adaptive LLM execution engine - intelligent routing, cascading, caching, and budget management
A small example package
LiteLLM adapter for Sefia.
A small example package
Structured thinking as a pluggable layer for any OpenAI-compatible API
Makes any LLM behave like a regular REST API. Define the contract, specllm enforces it.
Swap between LLM providers (Groq, OpenAI, Anthropic) through one interface, with automatic fallback and optional schema validation.
Envoy AI Gateway (API keys + usage reporting) plugin for Waldur Site Agent
A warp-speed, robust AI gateway
WatchLLM runtime orchestration and model routing.
A gateway that exposes local Wyoming services via OpenAI-compatible API endpoints
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
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.
Loopback bidirectional Anthropic/OpenAI API proxy with tool-call validation and multi-provider routing.
JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion. Unauthenticated calls are rejected.
Noir model — optional bounded single-shot LLM layer (anthropic / openai / openai-compatible); agent loops are impossible by design.