fresheyes is an open-source CLI tool that points a vision-capable AI agent at any web app and has it attempt a real user goal ("understand what this does and sign up") the way a skeptical newcomer would — by sight, not by reading the code. As it navigates, it narrates its confusion and decisions in real time, then produces a self-contained narrated HTML replay of the session plus a "rage-quit score" anchored to pre-generated, binary-checkable milestones. Beyond diagnosis, it generates tiered fixes — copy, layout, even SVGs — and in repo-aware mode proposes a reviewable change plan as a diff, never auto-editing. It supports both pre-login and logged-in reviews via locally saved browser sessions (credentials never touch the agent), and is extensible through markdown personas and MCP integrations like Figma and shadcn. The capstone: fresheyes built its own marketing site, then reviewed that site using itself.
- Vision-first agent that operates a live web app like a real first-time user, using a hybrid vision + element-map acting modelF1
- Real-time narration of friction, confusion, and decision-making as it navigatesF2
- Self-contained narrated HTML replay of every run — no video encoding or ffmpeg neededF3
- Rage-quit score anchored to 5 binary-checkable milestones generated before the run, with a --reuse-milestones flag for fair before/after comparisonsF4
- Tiered fix generation: copy rewrites, layout suggestions, and generated SVGsF5
- Repo-aware change plans — proposes a reviewable diff, never auto-edits your codeF6
- Pre-login and logged-in modes, with sessions saved locally and credentials kept out of prompts entirelyF7
- Swappable markdown personas (~20 lines each) as the main contribution surfaceF8
- MCP extensibility for design tokens, UI components, and media generationF9
- Built-in safety caps (--max-steps, --max-cost) and a consent gateF10
Next on the board · agent-company
Next project →Want one like this?
Tell me what you have in mind. We'll talk it through and agree a scope before anything gets built.