Model Access

Local RAG MCP Server with extended file support (including PPTX)

AI Agent node client — one-liner connects your machine to aawork.top, portal AI runs commands & files on your node, BYOK for 9+ LLM providers · AI Agent 节点客户端 — 一行命令让门户 AI 在你电脑上干活（跑命令/管文件），自带 key 畅用 9 家大模型

Zero-token-output decision router MCP server powered by TypeSafe Jev

The mosadd agent runner — turn a Supabase identity + an LLM key into a live mosadd contact that reads and replies to DMs. One command, your brand, no Hermes branding on the user's first install. Wraps the @mosadd/mcp tool handlers directly (no MCP-protoco

CHIP + Atom of Thoughts (AoT) Agent Harness — multi-provider n8n community node with a Process Analyst Worker for operational case triage (email, document, automotive service). Pluggable vaults (Obsidian, Supabase) and Human-in-the-Loop gate.

Pi Coding Agent (pi.dev) extension to access LLM models via Vikey.ai (Claude 3.7, DeepSeek R1/V3, GPT-4o, Gemini 2.0, Qwen, etc.)

CLI agent that containerizes GitHub repos on the fly, runs them in isolated Docker sandboxes, and exposes their CLIs as dynamic LLM tools.

The intelligent terminal agent that works with you.

Cairn — an AI that walks your system and leaves a trail of tests. Autonomous QA agent (UI today; API/unit/docs planned) powered by Claude/OpenRouter, with self-improvement via Langfuse.

Official Model Context Protocol (MCP) server for ModelGate: run LLM inference through the ModelGate gateway and inspect models, usage, cost and request traces from Claude, Cursor, VS Code and any MCP client.

Olly – Autonomous AI coding agent. Multi-step reasoning, file editing, shell execution, memory, skills & 15+ AI providers including TokenLB.

beecork — a from-scratch CLI coding agent: multi-model (OpenRouter), BYOK, path-confined tools, built part by part.

Local MCP server for the Unbox Gov Greek public procurement datasets (organizations, contracts, contract items, detection flags) on HuggingFace.

Let Claude plan and validate coding tasks while OpenCode CLI, driven by a free model, does the implementation. CLI + MCP server.

CLI + local MCP server for First Break AI — the first fully agentic AI cohort, where AI agents check your environment, validate your code, track progress, and answer questions. Powered by FetchLens.ai.

MCP server that sends one identical brief to several LLMs in parallel and returns every answer unmerged, unranked and unsynthesized, so the calling agent can see agreement and disagreement instead of an averaged blur.

MCP server for audio transcription via OpenRouter

🚀 REVOLUTIONARY AI-to-AI Collaboration Platform v6.1! NEW: Advanced Debugging Tools with Screenshot Analysis, Console Error Parsing, Automated Fix Generation, 5 Specialized Debugging Agents, Visual UI Analysis, JavaScript Error Intelligence, CSS/HTML Fix

Pay-per-use MCP server for AI agents — 18 API tools + smart LLM routing. No API keys needed, pay with USDC on Base.

Chat Model node for n8n — use a private LLM gateway as the LLM behind an AI Agent or LLM Chain (with tool calling).