ai-agent

wayfinder-router: Seamlessly Direct LLM Queries to Local or Cloud Models

A lightweight Python CLI that lets founders route AI queries deterministically between on‑prem and hosted LLMs, ensuring predictable performance and cost control.

From the repo · “Simple CLI tool for deterministic routing of queries between local and hosted LLM models”

418 stars24 forksPythonGuide quality 9/10 · reviewed Oct 11Updated 10/21/2026100% free · open source
What it does

Wayfinder-router efficiently routes queries between local and hosted large language models (LLMs) using a simple command-line interface

When to use it
  • •When you need to switch between local and cloud-based AI models for testing or production
  • •When you want to optimize query performance by routing them to the most suitable model
  • •When you have a mix of proprietary and open-source LLMs and need a unified interface
Ready-to-paste prompt
python wayfinder_router/cli.py -c sample_config.json -q 'Generate a short story about a character who discovers a hidden world'
Heads up: Make sure you have Python 3.8 or later installed, as wayfinder-router is not compatible with earlier versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/wayfinder-router && curl -fsSL https://workflowstacks.com/api/skills/wayfinder-router/claude-skill -o ~/.claude/skills/wayfinder-router/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How wayfinder-router: Seamlessly Direct LLM Queries to Local or Cloud Models works
Codeflow
Free to inspect

Wayfinder-router: Seamlessly Direct LLM Queries to Local or Cloud Models is a very large Rust project (~75k lines across 279 code files, plus 59 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~75k lines · 279 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Node.js · Docker
No API keys detected
Rust 62%Swift 24%TypeScript 5%Shell 4%JavaScript 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    package.json
    Dependencies and the commands it exposes
  3. 3
    examples/README.md
    A worked example — copy this to get going
What's in each folder
integrations/Sub-packages / plugins34 files
docs/Documentation36 files
examples/Examples you can copy4 files
macos/Folder124 files
clients/SDKs / client libraries116 files
rust/Folder114 files
decisions/Folder85 files
ios/Folder34 files
READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
itsthelore
Language
Python
Category
ai-agent
Published
6/17/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/wayfinder-router.svg)](https://workflowstacks.com/skills/wayfinder-router?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.