model-detection

Model Photovoltaic Fault Detector based in model detector YOLOv.3, this repository contains four detector model with their weights and the explanation of how to use these models.

LLM fingerprinting system that identifies the underlying LLM model family

🔍 Detect API model dilution and fingerprint which LLM is actually running behind any OpenAI-compatible or Anthropic endpoint

A self-hosted Codex CLI and Claude Code provider monitor that runs real CLI checks, captures HTTP request/response previews, and supports multi-provider management, scheduled model checks, WebUI, logs, backup, and REST API. 自托管的 Codex CLI 与 Claude Code 服务商监控工具，支持真实 CLI 检测、请求/响应捕获、多服务商管理、定时模型检查、WebUI、日志、备份与 REST API。

检测 DSH 账号被分配到哪个对话模型：为探测会话的实时思维链打分，判为旧模型的立刻中止。Detect which conversation model your DeepSeek Harness account is served, by scoring probe conversations' live chain-of-thought.

Identify the tokenizer family behind an AI API endpoint.

dsh gray-model detection plugin — launch N concurrent sessions, stream reasoning chains, auto-classify gray models (I'm+ing > Let me×5), normal models (Let me≥3), and abnormal models (no features). Supports standard/PTC/minimal/cordis presets.

Detect AI frameworks, LLM dependencies, and model files in any project. One command to know what AI is in your codebase.

Detect what model is really behind any OpenAI-compatible proxy, reseller or gateway. 6-way behavioral forensics - tokenizer fingerprint, trap-question bank, speed side channel, tool-call integrity - with no self-declaration needed. Zero-dependency single binary (Win/Linux/macOS), exit codes built for CI.

A zero-dependency Ruby gem that resolves LLM capabilities through a 4-tier hierarchy: empirical observation, OpenRouter's model index, RubyLLM registry, and provider heuristics.