Screenshot-to-JSON capture
Capture a selected area with the `⌘⇧S` shortcut, then copy the result as JSON for pasting into terminal-based tools.
SlimSnap
SlimSnap is a Mac app that turns screenshots into JSON for CLI coding agents such as Claude Code, Aider, and Codex CLI. It keeps capture and OCR local, and the site says the app is free with no registration required.
Overview
SlimSnap is a Mac app that turns screenshots into structured JSON for CLI-based coding agents. The product is positioned around a simple capture-and-paste workflow: select an area, annotate it if needed, copy the JSON, and paste it into tools that cannot accept images.
The site argues that this format is more useful than a raw screenshot for iterative debugging because it carries element text, positions, colors, and annotation intent in a form the agent can read directly. SlimSnap also publishes the JSON schema under MIT and describes a companion Claude Code skill that can auto-discover the latest capture from a local config file.
Features
Annotation support
Add arrows, callouts, and highlights so the exported JSON includes your intent, not just the pixels on screen.
Structured element data
Export normalized bounding boxes and OCR text for each element, so agents can refer to specific controls instead of guessing from an image.
Local processing
Keep capture and OCR local on your Mac, with no upload or account requirement in the described flow.
Open schema
Use the published MIT-licensed JSON schema or build your own exporter against the same format.
CLI-friendly handoff
Feed the output into Claude Code, Aider, Codex CLI, Cursor, or Continue.dev wherever text is accepted.
Use Cases
Frontend bug fixes
Capture a broken interface, point at the problem area with an arrow or callout, and hand the JSON to a coding agent that needs to edit the right file or component.
Terminal-agent handoff
Share an annotated screen state with Claude Code, Aider, or Codex CLI when the tool cannot accept images but still needs precise UI context.
Element-level UI reasoning
Move from a screenshot to a structured, machine-readable description of a form, dialog, or dashboard so the agent can reference specific elements by ID and bounding box.
Custom automation and extensions
Use the open JSON schema or the Claude Code skill as a starting point for custom workflows that consume SlimSnap output in other scripts or tools.
Pros and Cons
Pros
- Turns screenshots into a text format that terminal agents can read and act on.
- Keeps capture and OCR local on the Mac, with no upload or account requirement stated on the site.
- Includes annotations and intent text, which can reduce ambiguity when pointing to a specific UI element.
- Uses an open MIT JSON schema, which makes the output easier to inspect or extend.
- Designed to work with multiple CLI and editor agents, not just one assistant.
Cons
- Mac-only today, so it is not a cross-platform screenshot tool.
- The pricing page provided in the sources returns a 404, so there is no visible pricing breakdown to evaluate.
- Structured JSON is better for element-level fixes than for judging visual feel such as spacing, gradients, or overall aesthetics.
FAQ
Does SlimSnap work on Windows or Linux?
SlimSnap works on Mac today. The site says the app is Mac-only, and the Claude Code skill can also work with any valid SlimSnap JSON file.
Does SlimSnap upload screenshots to a server?
No. The site says capture and OCR run locally on your Mac, and screenshots never leave the machine.
What does SlimSnap cost?
The site says the app is free and does not require registration. The pricing page itself returns a 404, so no paid plan details are visible in the provided sources.
What does the JSON output contain?
SlimSnap creates JSON that includes screen metadata, detected elements, OCR text, bounding boxes, colors, and annotations. The site describes that output as something CLI agents such as Claude Code, Aider, and Codex CLI can read.
Is SlimSnap open source?
The site says the Mac app is closed source, while the JSON schema is published on GitHub under MIT. It also says the Claude Code skill is open and the app is closed.
Quick Facts
- Category
- Developer Tool
- Platform
- macOS
- Primary output
- JSON
- Primary users
- CLI coding agents and developers
- Source domain
- slimsnap.ai
- Availability
- Free, no registration required
Alternatives à SlimSnap
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Ghost
Ghost est un assistant IA en terminal pour discuter, générer du code et lancer des tâches en ligne de commande. Modèles gratuits, Linux, macOS, Windows, open source.