Ai Model Router V2

Automatically routes requests between local and cloud AI models based on task complexity and privacy, with auto-detection and context tracking.

Security Scan

The skill's code, files, and runtime instructions are internally consistent with an AI model router: it auto-detects local models, falls back to a cloud registry, performs simple privacy checks, and persists config/context under ~/.model-router.

Purpose & Capability

Name/description (route between local/cloud models, privacy, context) match the provided code. Detector reads Ollama config and returns a built-in cloud registry; router implements scoring, privacy checks, and model selection. File reads/writes (e.g., ~/.ollama/models.json and ~/.model-router/models.json) are expected for this purpose.

Instruction Scope

SKILL.md and usage examples instruct running the included Python CLI/library, which aligns with the code. The router does persist conversation contexts (contexts.json) and config (models.json) under ~/.model-router — this is within scope but important: conversation messages (truncated to 200 chars) are written to disk and could contain sensitive excerpts despite privacy-mode routing to local models.

Install Mechanism

There is no packaged install spec; this is effectively instruction + included source. install.sh is a harmless echo script. No network downloads, no package manager installs, and code is present in the skill bundle (read-only files included).

Credentials

The skill does not require environment variables to run. Some model entries include requires_api_key and api_key_env fields (e.g., ANTHROPIC_API_KEY) which are logical if you choose cloud models, but the skill does not demand them upfront. Detector reads only local files and does not perform network calls.

Persistence & Privilege

The skill creates and writes to ~/.model-router/{models.json,contexts.json} for config and conversation history. It does not request elevated privileges or system-wide changes and is not always: true. Persisting contexts/config in user home is expected but worth noting for privacy.

Assessment

This skill appears to do what it says: route tasks between local and cloud models and keep simple conversation context. Before installing, be aware it will: - Read ~/.ollama/models.json (if present) to detect local models. - Create and write ~/.model-router/models.json and ~/.model-router/contexts.json. Conversation messages are truncated to 200 characters but may still include sensitive fragments. - Offer cloud models that may require you to set API key environment variables (it does not automatically exfiltrate them). Recommendations: - If you handle secrets, consider disabling context tracking (don't pass conversation_id or set enable_context=False) or inspect/secure ~/.model-router/contexts.json. - Review the bundled Python files locally if you want to confirm behavior; they perform only file reads/writes and no network calls or subprocess execution. - If you plan to use cloud models, only set API keys as environment variables you trust and prefer provider-specific config rather than leaving keys in conversation text. Overall, the package is coherent and not suspicious, but exercise normal caution with persisted conversation data.

AI Model Router

Compact, intelligent model routing that just works.

Quick Start

# Install
npx clawhub@latest install ai-model-router

# First run - auto-detects your models
python3 skill/core/router.py "What is Python?"

# List available models
python3 skill/core/router.py --list

How It Works

Your Request → Analyze → Select Model
                          ↓
                    Simple? → Primary (fast/cheap)
                    Complex? → Secondary (capable)
                    Private? → Primary (forced)

Scoring (from model-router-premium)

Pattern	Points
Microservices, architecture	+10
Design, implement, optimize	+5
Explain, analyze, compare	+3
Syntax, example, "what is"	-3

Threshold: 5 (simple vs complex)

Features

Feature	Status
Auto-detect local models	✓ (Ollama, LM Studio)
Cloud model registry	✓ (7 built-in)
Privacy detection	✓ (API keys, passwords)
Context tracking	✓ (conversations)
JSON config	✓ (optional)
CLI interface	✓
Core code size	~200 lines

CLI

# Route a task
python3 skill/core/router.py "Design a system"
python3 skill/core/router.py "What is a for loop?"

# Options
--json                    # JSON output
--force primary           # Force primary model
--list                    # List all models
--status                  # Show status

Python API

from skill.core.router import RouterCore

router = RouterCore()
result = router.route("Design microservices")

print(result.model_name)   # "Claude Opus 4"
print(result.reason)        # "complex_task(score=15)"
print(result.confidence)    # 0.75

Configuration (Optional)

Create ~/.model-router/models.json:

{
  "primary_model": {"id": "ollama:llama3:8b"},
  "secondary_model": {"id": "anthropic:claude-opus-4"},
  "models": [...]
}

Without config: Auto-detects local + uses cloud registry.

Privacy Protection

Automatically forces primary (local) when sensitive data detected:

• API keys (sk-..., api_key)
• Passwords (password, passwd)
• Tokens (bearer, secret)
• Emails, SSN, credit cards

Files

• core/router.py - Core routing engine (~200 lines)
• modules/detector.py - Auto-detection (optional)
• modules/context.py - Context tracking (optional)

Inspired By

• model-router-premium: Simple scoring logic, cost-aware routing
• Model Router v1: Full feature set, documentation

This version combines:

• The simplicity of model-router-premium (~200 lines)
• The features of ai-model-router (privacy, auto-detect, context)