Model Router

    2

    Route AI tasks across providers with automatic fallback.

    Free

    4 installs5.0 (1 review)

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Model Router

    Example session with this skill installed

    I have Ollama running llama3:70b locally and an OpenRouter account. Set up a routing chain that prioritizes local for summaries but uses OpenRouter for complex refactoring.

    • Read your context and instructions
    • Compiled the model router

    I have generated a starter config at ~/.model-router/config.json. I mapped 'local-ollama' to the 'local' tier and 'openrouter' to the 'cloud' tier. I successfully validated both endpoints. Summaries will now route locally, falling back to cloud only if Ollama is unreachable.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A pattern-based decision framework that teaches AI agents how to intelligently route tasks across multiple model providers with automatic fallback.

    Key Features:

    • Multi-provider routing: Try cloud first, fall back to local providers automatically
    • Vendor-agnostic GPU detection: Works with NVIDIA, AMD, Intel, and Apple Silicon
    • Auto-discovery: Detect running providers (Ollama, LM Studio, llama.cpp, vLLM) on your machine
    • Zero dependencies: Helper scripts use Python stdlib only
    • Config-driven: Simple JSON or YAML config - bring your own providers and models
    • Task-tier routing: Route complex tasks to cloud, simple queries to local - save API costs

    What's included:

    • SKILL.md decision framework
    • Discovery script (auto-detect GPU + providers)
    • Probe script (check provider health)
    • Route validator (test your full chain)
    • Annotated config template

    Perfect for developers running local LLMs alongside cloud APIs who want a reliable fallback when their primary provider is rate-limited or down.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    4 people have installed this skill.

    Trust & safety

    Security scanned

    Verified clean 1 month ago

    • Free to download with an account

    Requires

    Openrouter
    Python

    Listed1 month ago
    Updated1 month ago

    What's inside

    Frequently Asked Questions