modlens
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
Learn how ModLens recovers pasted images from LLM harness session storage. It uses process inspection, harness-specific adapters, and secure file writing for efficient retrieval.
How ModLens Uses extraBody Configuration to Pass Provider-Specific OptionsDiscover how ModLens extraBody configuration passes provider-specific options to OpenAI, Gemini, and Anthropic. Deep-merge JSON payloads securely without altering core code.
How to Set the Proxy Configuration for ModLens API ProvidersLearn how to set proxy configuration for ModLens API providers. Explore global, per-provider, and environment variable settings with provider-specific overrides.
How ModLens Chains Vision Providers for Failover: Provider Selection Logic ExplainedDiscover how ModLens chains vision providers for failover. Learn about its provider selection logic, prioritizing local over remote and respecting user preferences for a robust sequence.
ModLens VisionProvider Interface: Methods, Types, and Implementation PatternsExplore the ModLens VisionProvider interface, its key methods like buildInvocation and execute, and understand how it unifies subprocess and in-process API execution patterns.
How to Set Up and Use the antigravity-cli Provider in ModLensLearn how to set up and use the antigravity-cli provider for ModLens. Process images with Google Gemini in 15-45 seconds using this keyless backend.
CLI-Based Providers in ModLens: How They Work and When to Use ThemUnderstand ModLens CLI providers antigravity-cli claude-cli and kimi-cli Analyze images using external command-line tools and get structured JSON evidence for LLM workflows.
How to Use the Anthropic Provider in ModLens with an Existing API KeyLearn how to use the Anthropic provider in ModLens with your existing API key. Easily configure via config file or environment variable for seamless vision analysis.
Characteristics of the Gemini-API Provider in ModLens: In-Process Vision AnalysisExplore the gemini-api provider in ModLens, an in-process vision solution executing HTTP requests to Google's Gemini API with JSON schema validation and support for local/remote images.
The Six Built-In Providers in ModLens: Complete Configuration GuideExplore the six built-in ModLens providers antigravity-cli gemini-api openai anthropic claude-cli and kimi-cli for flexible image analysis. Configure local or remote processing easily.
How to Install and Uninstall ModLens as a Skill PluginInstall and uninstall ModLens as a skill plugin by copying its folder into your AI harness skills directory. Access the modlens vision command easily without system package managers.
ModLens Integration Requirements for Host Applications: A Complete GuideLearn ModLens integration requirements for host applications. Provide image input, configure a vision provider, and invoke the CLI for JSON evidence. A complete guide for developers.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →