Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Screen memory without screenshots, just text to Markdown

Details

External ID
49429095
Source
HN
Company
—
Product
Screen memory without screenshots, just text to Markdown
Website domain
github.com
Launched
Aug. 25, 2026
Cohort
—
Upvotes
62
Upvotes percentile
0.8830645161290323
Tags
—
Fetched at
Sept. 10, 2026, 5:32 a.m.
Updated at
Sept. 10, 2026, 5:32 a.m.

Description

It's a macOS menu bar app that reads the text of your focused window every few seconds through the Accessibility API. No screenshots, no video, or OCR. It writes plain markdown, one file per day, into a folder you choose.Point Claude Code (or anything with file access) at the folder and ask "what did I work on Tuesday?" or have it build memory about your projects. The folder contains an AGENTS.md explaining the format to the model.Thought it might be useful for someone so chucked it up on GitHub

Enrichment

Theme
markdown editors and writing tools
Vertical
Horizontal
Function
Dev tools
Audience
Developer
AI stance
AI feature
Project type
Hobby / open-source project
Normalized one-liner
screen capture as markdown text instead of screenshots
Manually corrected
False

Could you build this?

Yes A macOS menu bar utility querying the native Accessibility API (AXUIElementCopyAttributeValue) on a timer and appending text to Markdown files can be vibe-coded in Swift in an afternoon.

Discussion

20 comments analyzed.

Competitors mentioned: Slimsnap.ai (screenshot-based approach), ActivityWatch (focused window tracking), Rem (screenshot + OCR with time-travel search), Appshots (accessibility API text extraction)

Concerns raised: Per-app breakage in text extraction accuracy, Accessibility API not supported in all situations, Loss of visual history and time-travel search features, Lossiness of accessibility tree vs. pixel-based approach, Energy efficiency vs. accessibility API methods

Feature requests: Context-aware dictation integration with local LLM, Swipe to go back in time and visually search history, Fine-tuned vision model for UI reasoning (fully local), Integration with structured data sources (git, Slack, emails, tickets)

Competitors

Other products that read as similar to this one — 363 launches clear the similarity bar, closest 8 shown.

Attention rank: #97 of 364 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 269 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a dev tools tool for Sales yet.