OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.
Anyray connect — points local coding tools (Claude Code, Cursor, Windsurf, SDKs) at the Anyray gateway by writing their base URL + a placeholder key. The gateway stays the brain; this is just the on-ramp.
AI Setu client — drop-in OpenAI SDK with workspace credit accounting and multi-provider routing.
HasteKit - AI Gateway
AI Setu MCP server — exposes the AI Setu gateway and control plane as Model Context Protocol tools for Claude Code and any MCP-aware agent.
Lightweight AI gateway daemon orchestrating Claude Code, Codex, Grok, and Antigravity CLI
AI Setu CLI — shell-friendly wrapper over @ai-setu/admin for scripts and CI.
Typed SDK for the Builderforce.ai LLM gateway — chat completions with tool-calling and structured output, embeddings, image generation, models, and usage analytics over an OpenAI-compatible surface.
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.
Community Vercel AI SDK provider for the Neon AI Gateway.
DeepClaw observability plugin for OpenClaw — real-time LLM usage, token, cache, reasoning, and cost telemetry.
TrustGate Node.js SDK with Shadow AI detection and workflow context
Command-line tool for AIgateway — one API, every model. Installs the aig binary.
One-click TokenOpen configuration for Claude Code, Codex, OpenClaw, Hermes, and OpenAI-compatible developer tools.
Enterprise MCP Governor — unified AI tool governance: auth, injection scanning, PII masking, audit logging.
Multi-model + multi-judge consensus for AI agents over MCP — ask 2–6 frontier LLMs, score them with a judge panel, and get one verified answer, with blind-spot (disagreement) detection, EU/sovereignty routing and single-model passthrough. For Claude Code,
AI Agents discover, invoke, and settle paid LLMs, APIs, and Skills — starting with Skill Boss. No manual key setup. No prepayment. Pay-per-call via x402 or Agent Card.
Open Gateway Protocol (OGP) - Peer-to-peer federation daemon for OpenClaw AI gateways with cryptographic signatures
Migrate LiteLLM entities (models, organizations, teams, users, virtual keys) into Bifrost
Vercel AI SDK provider for Coder AI Gateway. Point the AI SDK at your Coder deployment with a Coder API token and use any model your deployment proxies — across AI Gateway's OpenAI- and Anthropic-compatible surfaces.
Open-source smart LLM router for the Omnicall gateway. npx omnicall-router works FREE out of the box — point any OpenAI client at it, send model "auto", and it routes to the cheapest of 248 capable models. Pass a funded gck_ key to unlock all 248 pay-pe
Omnicall — every AI tool your agent needs in one keyless endpoint: 248 LLMs (GPT, Claude, Gemini, Grok, DeepSeek, Llama) + image/video/voice/music generation + live crypto/DEX/DeFi/markets/web/research. Pay-per-call in USDC, no API key, no signup. One-lin
CLI tool for Unbound - AI Gateway management