whereismyai
ModLens
ModLens is a computer vision plugin that provides text-only coding agents with image understanding by transcribing visual data into structured text.
ModLens acts as a bridge to grant visual capabilities to text-based coding agents. It processes images, screenshots, charts, and clipboard content by extracting specific text, layout information, and visual cues. The tool transcribes visual input into structured JSON data, allowing agents to process data with greater precision. It integrates directly with tools like DeepSeek and supports various API endpoints including Gemini, OpenAI-compatible services, and Claude. This plugin is designed for developers who need their automated agents to interpret visual context alongside code.
ModLens at a glance
- Best for: Software engineer
- Runs on: CLI
- Pricing: Free
- Released: February 2026
- Category: AI coding tool
- Website: liustack.dev
Key features
- Generates structured JSON output from image inputs
- Integrates with DeepSeek
- Supports Gemini, OpenAI-compatible endpoints, and Claude API
- Processes screenshots, charts, and clipboard images
- Handles batch file processing
- Provides layout partitioning and semantic cues
Use it for
- Adding visual understanding to text-based coding agents
- Converting screenshots into machine-readable data
- Analyzing charts and visual documentation for coding tasks
Alternatives to ModLens
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- ModVet — Scans Claude Code mods offline in milliseconds with zero dependencies.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- CodeCompanion — Provides native AI integration and agent support directly within Neovim.
- opencode.nvim — Keeps AI interactions within the existing Neovim environment and workflow.
- claudecode.nvim — Adds native AI coding assistant functionality to Neovim.
- claude-mem — It shares persistent, searchable agent memory across sessions and devices.
- Agent Vision Toolkit — Gives text-only coding agents task-aware sight
- PulseDev — Edits local source files directly through existing coding agents based on visual web clicks.
- AGENTS.md — It separates agent-specific instructions from human-focused README files.
- opcode — Turns terminal Claude Code workflows into an intuitive visual interface.
- PR Lens — Reviews pull requests faster using animated architecture and data flow diagrams.
All ModLens alternatives