Model Access

Coding agent for your terminal, with any model: one Abacus AI plan, your ChatGPT subscription, your own API keys, or local models.

Expose remote MCP server tools (Streamable HTTP / SSE) as tools for @openrouter/agent's callModel, with serializable caching and pluggable auth.

Atlarix CLI: an AI coding agent in your terminal. Works with any model (Atlarix Auto, your own API key, or a local model) and runs unattended with `atlarix run` for CI.

OpenAI-compatible inference for open-weight models, set up by your coding agent. Prepaid, pay per token, no subscription. US live; Canada coming soon.

Query OpenRouter (free key; set OPENROUTER_API_KEY, Bearer): model list, key info, credits.

Fast, cheap, probability-scored decisions for coding agents, scripts and CI: a CLI and MCP server for the OpenAI Decisions API and Jev (TypeSafe AI)

Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.

Pre-checks a model change before GPU time or traffic: memory, layout, serving config, pins.

MCP gateway: many servers, one policy, lethal-trifecta blocking, PII masking, audit log

A production-grade MCP server for IBM i

The coding agent you can undo: 250+ models in your terminal, parallel swarms, model racing, and /undo for everything, even shell commands.

Convert animated SVG (CSS/SMIL) to video (MP4/WebM) or image (GIF/aPNG) with in-band delivery.

A Model Context Protocol (MCP) server for OpenRouter API with Collective Intelligence - Multi-model consensus, ensemble reasoning, and collaborative problem solving

n8n nodes for DzRouter: 200+ AI models (GPT, Claude, Gemini, DeepSeek, Llama) through one API key, billed in Algerian dinars. Chat, AI Agent chat model, text tools and model catalog.

Unified AI toolkit: one API for OpenAI, Anthropic, Gemini, Mistral, Cohere, NVIDIA and OpenAI-compatible services, with a tool loop, structured output, generators for web developers and an MCP server.

MCP: OpenRouter, Groq, Cerebras, Sail, Nous Research, QwenCloud, DeepInfra, Novita, SambaNova, Chutes, WaveSpeedAI, fal, Higgsfield, KIE, Crazyrouter, AkashML, io.net, ElevenLabs, Cartesia. Refuses to quote Sail prices. GitHub trending; Jev router.

Open-source agent orchestration layer — the AI company OS. Local model agent engine (GGUF/Ollama/llama-server), HuggingFace model browser, MCP integrations (Slack, Gmail, Stripe, 15+), agent scheduling (cron), business roles (CMO, CFO, EA). GUI dashboard,

Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.

Lint Jev and Luna decision-model questions, or ask the model to check them with your key.

Official Hugging Face MCP Server