← 返回 Skills 市场

Ai Model Router V2

Name: Ai Model Router V2
Author: yuldrone

作者 yuldrone · GitHub ↗ · v1.1.0 · MIT-0

cross-platform ✓ 安全检测通过

250

总下载

当前安装

版本数

在 OpenClaw 中安装

/install ai-model-router-v2

功能描述

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

使用说明 (SKILL.md)

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)

安全使用建议

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.

功能分析

Type: OpenClaw Skill Name: ai-model-router-v2 Version: 1.1.0 The skill bundle implements a model routing utility designed to switch between local and cloud AI models based on task complexity and privacy requirements. The code in 'skill/core/router.py' and 'skill/modules/detector.py' is well-structured, lacks dangerous execution sinks (such as eval or subprocess), and performs only read-only operations on standard local configuration paths (e.g., ~/.ollama). The privacy detection feature is a security benefit, as it identifies sensitive patterns like API keys and passwords to ensure they are processed locally rather than sent to cloud providers.

能力评估

✓ 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.

ℹ 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).

ℹ 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.

ℹ 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.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install ai-model-router-v2
安装完成后，直接呼叫该 Skill 的名称或使用 /ai-model-router-v2 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.1.0

ai-model-router-v2 version 1.1.0 - Updated package metadata in package.json. - No functional changes to code or documentation.

v2.0.1

- Improved local model auto-detection logic in detector.py. - Minor internal update; no changes to CLI, API, or configuration usage. - Documentation and feature set remain unchanged.

v2.0.0

ai-model-router-v2 2.0.0 - Major update combining the simplicity of model-router-premium and advanced features from ai-model-router. - Adds automatic detection of local AI models (Ollama, LM Studio). - Intelligent routing now considers task complexity, privacy triggers (API keys, passwords), and user model switching requests. - Built-in cloud model registry with 7 options and optional JSON config for custom setups. - Privacy mode automatically routes sensitive queries to local models for enhanced security. - Lightweight, CLI-driven design with a simple Python API, preserving advanced features in ~200 lines of core code.

元数据

Slug ai-model-router-v2

版本 1.1.0

许可证 MIT-0

累计安装 2

当前安装数 2

历史版本数 3

常见问题