# cccyd2003-qwq/pinkbin

扫盘 · 看懂 · 删除。磁盘扫描+清理Agent（Tauri 2 + React + Rust）

Repository: https://github.com/cccyd2003-qwq/pinkbin
Canonical: https://ross.abutalabs.com/products/pinkbin
Homepage: https://github.com/cccyd2003-qwq/pinkbin
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, conda, disk-analyzer, disk-cleaner, open-source, react, rust, tauri, wechat, windows
Last push: 2026-07-14T15:34:49+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 51, longevity 8
- inputs: {"age_days": 123, "days_push": 50, "days_rel": 119, "gap_med": null, "n_releases_24m": 1}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1343, forks 54 (observed 2026-08-28T04:04:26.470035+00:00)

## What it is
Pinkbin is an open-source Windows disk analyzer and cleaner built with Tauri 2, React, and Rust. It scans entire drives in seconds via direct NTFS MFT reads, lets users drag unknown folders to an AI (BYOK: Anthropic/OpenAI/Gemini/Ollama) for explanation of what is safe to delete, and offers scoped cleanup scripts for apps like WeChat and Conda—always sending only directory metadata, never file contents, and deleting to the recycle bin by default.

## Use cases
- find what is taking up disk space on windows
- clean up wechat files and caches
- figure out what an unknown folder is before deleting it
- free up space used by conda environments
- visualize disk usage with a treemap
- ai-assisted disk cleanup
- safely delete large folders to recycle bin

## When to choose
- you are on Windows 10/11 and want a fast, privacy-respecting disk cleaner
- you want AI to explain unfamiliar folders using only metadata, with your own API key or local Ollama
- you need targeted cleanup scopes for WeChat or Conda
- you prefer open-source tools that never read file contents

## When to avoid
- you need prebuilt binaries for macOS or Linux (only self-build supported there)
- you want fully automated background cleaning without manual review
- you cannot provide an LLM API key or run Ollama and need AI analysis
- you need deep file-content analysis rather than metadata-based suggestions

## Facets
- artifact type: application
- maturity: active
- function: file-system, llm-inference, chatbot, gui, developer-tools
- domain: files, developer-tools, artificial-intelligence, windows, privacy
- platform: windows, rust, cross-platform
- tags: disk-cleaner, disk-analyzer, tauri, ai-assistant, byok, ntfs-mft, wechat-cleanup, conda-cleanup, treemap, recycle-bin, desktop

## Member repositories
- cccyd2003-qwq/pinkbin (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:26.470035+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:42:53.580313+00:00, confidence not recorded.
  - readme: https://github.com/cccyd2003-qwq/pinkbin (fetched 2026-08-28T04:04:26.470035+00:00, sha 5379d6118f3c)
  - homepage: https://github.com/cccyd2003-qwq/pinkbin (fetched 2026-08-29T12:02:36.052604+00:00, sha a07d72b0aa94)
- Data as of 2026-08-30T08:39:29.467469+00:00.