Agent frameworks & infrastructure
LLM gateways & API proxies
4,018 agents · most starred first
LLM gateways & API proxies, page 38 of 41
Provider-routed LLM request retry policy for the DeepSeek Harness
Veryfront first-party extension package for ext-llm-google
Provider-routed LLM request retry policy for the DeepSeek Harness
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.
LangChain integration for Leanroute. Drop-in `ChatLeanroute` chat model — same interface as `ChatOpenAI`, but routes across 14 LLM providers (OpenAI, Anthropic, Google, DeepSeek, Groq, xAI, and more) with cost caps, failover, and MCP support baked in.
Provider connections for the Axon agent runtime — Anthropic, OpenAI, Google, Groq, Ollama and more.
TypeScript SDK for Verlon AI — the managed AI infrastructure platform that routes requests across LLM providers, evaluates response quality, runs experiments against live traffic, and auto-tunes routing configurations. Agent integration protocol: https://
The official TypeScript library for the OpenAI API (with updated dependencies)
OpenAI provider adapter for FDEKit
Generated UTDK provider client for OpenAI API. The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details.
OpenAI-compatible ModelAdapter for nestjs-agentic. Works with OpenAI and any Chat Completions compatible endpoint such as Azure OpenAI, Ollama, vLLM, Groq, Together, OpenRouter, and LM Studio.
DeepSeek Harness plugin: learning agentic router — rule + UCB + LinUCB + k-NN experts under an EXP3 meta-selector, with a durable quality-reward flywheel, REAL model switching via the session request-header precedence chain, and STEP-LEVEL routing (v1.5.0
Cost-aware multi-provider LLM router with role tiers (cheap/mid/chief/audit).
Production-grade Gemini API key rotation with cooldown, exponential backoff, RPM tracking, and persistent stats.
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.
Policy-aware LLM routing, transports and drive strategies extracted from Koru.
LangChain integration for OpenZoo - OpenAI-compatible inference with no signup
Official xAI Responses API package for llm-api-adapter
Concurrent, caching, retrying OpenAI-compatible batch chat-completion runner with structured output validation.
A local proxy circuit breaker to stop runaway AI agents from burning API budgets.
Deterministic pre-filter + cheap→chief escalation pipeline — send only the few items that matter to your expensive model.
LLM plugin for models hosted by OpenZoo - no signup required
Use the Codex CLI's ChatGPT login (~/.codex/auth.json) as a bearer credential for the Codex backend
LiteLLM provider backend for purrcept_core.
High-throughput LLM Gateway and Circuit Breaker for distributed AI agents
OpenAI-compatible chat model for Semora: official openai SDK, LangChain chunks.
Proxy inteligente entre APIs compatíveis com OpenAI e múltiplos provedores de LLM, com roteamento por complexidade e compressão de contexto.
A unified interface to all major LLM providers with system certificate and async support
LiteLLM (virtual key lifecycle + usage reporting) plugin for Waldur Site Agent
Standalone cross-provider translation router for AI-agent hooks with ordered fallbacks and shared caches
Veryfront first-party extension package for ext-llm-anthropic
Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit
Evidence-driven multi-agent routing with deterministic safety gates.
This is an LLM wrapper for claude and its subscription to use via Programming
Quota-aware failover proxy for Claude Code: spills over from Anthropic to Ollama Cloud when your quota runs low, and switches back once it recovers.
Register Anthropic-protocol-compatible providers as first-class llm models
LLM plugin for models hosted by Hubris
Generic OpenAI-compatible inference provider for the NucleusIQ AI agent framework (vLLM, SGLang, TGI, llama.cpp, LM Studio, NIM, and OpenAI-compatible clouds).
Official Anthropic Messages SDK adapter for PurrA
Official OpenAI Responses and Chat Completions SDK adapter for PurrA
One client for every OpenAI-compatible LLM server - local (Ollama, LM Studio, vLLM, llama.cpp) or hosted (OpenRouter, OpenAI) - with images and audio as plain message parts.
Active Loader-backed plugin package inventory for official DeepSeek LLM API requests
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Reusable model provider adapters and streaming runtime from OpenClaw
ChatGPT OAuth and Codex models for DeepSeek Harness.
Unified LLM API with automatic model discovery and provider configuration
LLM API 中转网关:配置文件配置多家运营商模型,对外暴露统一 OpenAI 兼容接口
The Z.AI provider for the AI SDK contains language model support for Z.AI's GLM models.
OpenAI adapter for agentic-auto-correct.
Anthropic Claude adapter for agentic-auto-correct.
Groq LLM client for AI-Parrot (parrot.clients.groq)
vLLM (OpenAI-compatible) LLM client for AI-Parrot (parrot.clients.vllm)
Athena LLM client — one seam across frontier, hosted-open (with failover), and local backends
Renamed to claudexer -- see https://pypi.org/project/claudexer/
Unified LLM client for every major provider - one API, spec-driven wire format, real cost tracking.
Conduit — lightweight AI driver for OpenAI-compatible, Ollama, Anthropic, Gemini (Python)
One API. Every AI. Pay per call. Python client for DexL Agents.
Durable, self-healing multi-provider LLM gateway and circuit breaker with autonomous failover, tool idempotency, and context compaction for AI agents (Claude Code, Hermes, OpenClaw, OpenCode).
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
LiteLLM provider backend for purrcept_core.
LLM Router – core library with optional API and metrics
Point vLLM (or any OpenAI-client-based consumer) at Algenta's own OpenAI-compatible /v1/chat/completions and /v1/responses surface -- a thin base-url/api-key helper plus a real, honest capability-fidelity conformance suite
Universal OpenAI adapter and provider plugin for ai-agent-sdk
Universal Anthropic adapter and provider plugin for ai-agent-sdk
Universal Gemini Interactions adapter and provider plugin for ai-agent-sdk
Universal Gemini Interactions wire schema, serializer, and SSE translator for ai-agent-sdk
Universal fetch, SSE, configurable provider, and provider-attempt accounting for ai-agent-sdk
Universal Anthropic Messages wire schema, serializer, translator, and dialect for ai-agent-sdk
Universal OpenAI Responses and Codex wire schema, serializer, translator, and dialect for ai-agent-sdk
Universal Codex adapter, OAuth, injected auth contracts, and provider plugin for ai-agent-sdk
Additive request-field registry for the official DeepSeek LLM API adapter
Runtime-local LLM route tool-call projection metadata for DeepSeek Harness integrations.
Creates an http/s/socks proxy agent
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.
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.
Pi-native OpenAI Codex subscription model provider plugin for Assembly Line.
Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion for the verified caller.
Self-hosted LLM gateway and SDK for Node — a LiteLLM-style unified API for 16 providers (Anthropic, OpenAI, Gemini, Mistral, Groq, xAI, DeepSeek, OpenRouter, …) with per-call USD cost tracking, streaming, tool calls, vision, speech-to-text, and built-in O
Local-first OpenAI-compatible gateway and control plane for an authorized Postman web session.
Personal LLM API gateway & proxy — one address + one API key for all your models. Forwards OpenAI & Anthropic calls to your backends with failover and a circuit breaker. Pure passthrough, no format translation. Self-hosted (CLI + web UI).
Convert DeepSeek Web Chat to an OpenAI-compatible local API and interactive CLI for any harness or agent
Self-hosted Anthropic- and OpenAI-compatible API backed by your signed-in coding-agent CLIs, plus a zero-config library for driving them from your own apps — no API keys needed.
TokenRouter.com unified API gateway as a native Pi provider for accessing 300+ LLM models via a single API key
A lightweight runtime that unifies 490+ AI providers behind a single, OpenAI-compatible API.
Unified LLM API with automatic model discovery and provider configuration
AgentRouter provider for pi — GPT-6 Astra, GPT-5.6 Sol, Claude Opus 4.8/5, DeepSeek V4 Flash and GLM 5.3 under one namespace, with self-healing WAF recovery (history redaction + auto-translation)
Secure OpenAI Key Proxy (SOAKP) facilitates secure usage of the OpenAI API key through a proxy-like application.
Unified LLM API with automatic model discovery and provider configuration
Process-wide outbound HTTP proxy policy for DeepSeek Harness: resolve it from the launch environment and install it as undici's global dispatcher
The **GMI Cloud provider** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for [GMI Cloud](https://www.gmicloud.ai), offering GPU inference for open-weight models over an OpenAI-compatible API.
A robust three-tier LLM-aware caching SDK using Redis, ChromaDB, and automatic SQLite bootstrap.
Pre-inference routing for tool-rich LLMs and multi-agent systems with MCP, A2A, LangGraph, AutoGen, policy-aware routing, recovery, and reproducible evaluation.