visual-feedback

AI-powered annotations for localhost development. Create visual feedback on your apps and let AI coding agents automatically implement fixes via MCP integration.

Drop-in visual feedback widget for websites. Pin comments directly on page elements — Shadow DOM isolated, framework-agnostic.

Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement and adversarial visual review for high-fidelity art and method figures. Skills for Claude Code and Codex.

Drop-in toolbar for any website — annotate the UI and capture selectors, computed styles, React component trees, and screenshots as an agent-ready prompt.

Give your AI coding agent eyes and ears. Screen + voice capture → structured Markdown. MCP server, CLI, and macOS app.

A shared visual canvas for Claude Code — draw, diagram, and get visual feedback through CLI commands and an interactive browser UI.

Sight-reading piano practice with interactive sheet music (Windows, USB-MIDI).

Vynix MCP server. Give AI coding agents access to your visual feedback and bug reports.

Visual browser element annotation for DeepSeek Harness, capturing DOM, styles, accessibility data, comments, and viewport screenshots. DeepSeek Harness 浏览器元素标注插件，捕获 DOM、样式、可访问性数据、评论和视口截图。

Visual feedback loop for Spec-Driven Development: SVG wireframe generation, review, and sign-off that become spec constraints honored by /plan, /tasks, and /implement.

Drop a pin on any UI element, write what to change, and your AI coding agent edits the source. In-browser visual annotation for Claude Code, Cursor, and any MCP agent — web + Electron.

Visual feedback & website critique tool for design mockups.

Visual terminal feedback for AI coding sessions — background colors, tab titles, animated faces, and session identity icons for Claude Code, Gemini CLI, OpenCode, and Codex CLI

Turn precise browser redlines into verified UI fixes in Claude Code and Codex — Chrome extension, local sidecar, and agent plugins.

A curated collection of multimodal agentic coding—vision as feedback for building, verifying, and repairing executable artifacts.

In-page review overlay for React and Next.js apps: pin comments to any DOM element of a preview deployment, bring your own database.

Research prototype for webcam-based interocular ratio tracking and visual feedback for strabismus self-awareness.

Draw on your live website. Freehand feedback for AI agents.

An inclusive running concept using visual and haptic feedback to make important race signals more accessible for people with hearing impairments.

Interactive visual in-context prompting Chrome extension for live websites. Point, click, persist multi-page annotations, and bridge directly into Antigravity AI agents.