Keyword: ai-gateway
- @jeffreycao/copilot-apiReleased11h agoVersion1.13.10
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
- adaptive-memory-multi-model-routerReleased14h agoVersion2.14.60
RouterArena #1 among known public baselines: 96.77% accuracy, $0.0768/1K, 1.0000 robustness. OpenAI-compatible LLM router across 47+ providers.
- anyray-connectReleased1h agoVersion0.11.9
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/clientReleased4d agoVersion0.16.1
AI Setu client — drop-in OpenAI SDK with workspace credit accounting and multi-provider routing.
- @hastekit/ai-gatewayReleased6h agoVersion0.0.33
HasteKit - AI Gateway
- @ai-setu/mcpReleased4d agoVersion0.16.1
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.
- jinn-cliReleased3d agoVersion0.23.3
Lightweight AI gateway daemon orchestrating Claude Code, Codex, Grok, and Antigravity CLI
- @ai-setu/cliReleased4d agoVersion0.16.1
AI Setu CLI — shell-friendly wrapper over @ai-setu/admin for scripts and CI.
- @seanhogg/builderforce-sdkReleasedyesterdayVersion2026.6.29
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.
- @nick3/copilot-apiReleased23h agoVersion1.13.7
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers.
- lynkrReleased2 weeks agoVersion9.5.0
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.
- @neondatabase/ai-sdk-providerReleased6d agoVersion0.5.0
Community Vercel AI SDK provider for the Neon AI Gateway.
- deepclaw-openclawReleasedyesterdayVersion0.1.3
DeepClaw observability plugin for OpenClaw — real-time LLM usage, token, cache, reasoning, and cost telemetry.
- @trustgateai/sdkReleased6d agoVersion1.7.0
TrustGate Node.js SDK with Shadow AI detection and workflow context
- aigateway-cliReleased6d agoVersion0.2.0
Command-line tool for AIgateway — one API, every model. Installs the aig binary.
- tokenopen-configReleased3h agoVersion0.1.1
One-click TokenOpen configuration for Claude Code, Codex, OpenClaw, Hermes, and OpenAI-compatible developer tools.
- mcp-governorReleased2d agoVersion0.0.3
Enterprise MCP Governor — unified AI tool governance: auth, injection scanning, PII masking, audit logging.
- tokonomix-council-mcpReleased26m agoVersion1.8.2
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,
- @aeon-ai-pay/aigatewayReleased3d agoVersion0.4.1
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.
- @dp-pcs/ogpReleased4d agoVersion0.11.4
Open Gateway Protocol (OGP) - Peer-to-peer federation daemon for OpenClaw AI gateways with cryptographic signatures
- @maximhq/bifrost-migration-cliReleased4d agoVersion0.1.0
Migrate LiteLLM entities (models, organizations, teams, users, virtual keys) into Bifrost
- @coder/ai-sdk-providerReleased4d agoVersion0.2.0
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.
- omnicall-routerReleased3d agoVersion1.2.1
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-mcpReleased5d agoVersion1.0.1
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
- unbound-cliReleased3h agoVersion1.9.0
CLI tool for Unbound - AI Gateway management