# lemonadesaltbagel/crab

> A toolkit for clean-room reimplementation of app features from behavior rather than source: an observer agent studies the app as a black box, and a second agent implements only from a sanitized spec.

- Magnitude: 1.9 out of 10 — Steady
- Stars: 160 total · +3 stars measured 2026-11-03, 00:36–05:35 UTC, ≈ 16 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: Apache-2.0 · Created: 2026-10-22 · Last push: 2026-11-03
- GitHub: https://github.com/lemonadesaltbagel/crab · Homepage: https://pypi.org/project/crab-cleanroom/ · Page: https://gitnova.dev/en/r/lemonadesaltbagel/crab

## Useful for

- Rebuild a third-party feature in your own product without copying code
- Verify a clone against the original via abstract pass/fail verdicts
- Record coverage and observation gaps in a signed audit log

## Why it’s here

- Star-counter measurements on 2026-11-03 (UTC), 00:36–05:35: 157 → 160 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +16 stars, using observed gains and the previous day.
- The repository is 12 days old and already has 160 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 26
- Issues and pull requests: 0
- Watchers: 21
- Average over the last week: 15 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 0

## Stars per day, last 13 days (oldest → newest, today is partial)

2026-10-22 … 2026-11-03: 0, 0, 0, 23, 34, 12, 12, 12, 19, 12, 18, 18, 3

## Magnitude by day, last 8 days

10-27 3.1, 10-28 2.5, 10-29 2.0, 10-30 2.0, 10-31 2.6, 11-01 2.4, 11-02 2.2, 11-03 2.0

## More in this category

1. **storytold/craft-anything** — 9.3 · Breakout · AI agents · Rust · +890 stars measured 2026-11-03, 00:30–05:30 UTC, ≈ 3,440 by evening
   A pure-Rust reverse-engineering engine with 284 tools that inspects websites, apps and games, then has a coding agent rebuild a similar version and checks the result against the original.
   Full card: https://gitnova.dev/en/r/storytold/craft-anything.md
2. **vercel-labs/agent-desktop** — 9.3 · Breakout · AI agents · Rust · +907 stars measured 2026-11-03, 00:30–05:30 UTC, ≈ 3,396 by evening
   Rust CLI that lets AI agents control desktop apps via macOS accessibility trees, with stable element refs and a snapshot-to-action loop. Combines a native binary with a C-ABI cdylib for Python/Swift/Go/Node bindings.
   Full card: https://gitnova.dev/en/r/vercel-labs/agent-desktop.md
3. **pingdotgg/t3code** — 8.9 · Breakout · AI agents · TypeScript · +503 stars measured 2026-11-03, 00:30–05:30 UTC, ≈ 2,907 by evening
   T3 Code is an agent harness control surface for agents on your machine, with mobile (iOS, Android), web and Electron desktop apps. It works with your Claude Code, Codex, Cursor, Grok Build, OpenCode and Google Antigravity subscriptions if…
   Full card: https://gitnova.dev/en/r/pingdotgg/t3code.md
4. **deepseek-ai/dsh-superagent-prototype** — 8.6 · Peaking · AI agents · TypeScript · +1,060 stars measured 2026-11-03, 00:30–05:30 UTC, ≈ 4,255 by evening
   Research prototype of a proactive coding agent for a single GitHub repository, packaged as a bundle for DeepSeek Harness: it listens to GitHub and Feishu, opens work items and replies in the original conversation, for example with a pull…
   Full card: https://gitnova.dev/en/r/deepseek-ai/dsh-superagent-prototype.md
5. **Orkas-AI/Orkas** — 8.1 · Breakout · AI agents · JavaScript · +779 stars measured 2026-11-03, 00:31–05:30 UTC, ≈ 1,890 by evening
   A local-first desktop app with a team of AI agents: a Commander turns a goal into to-dos and coordinates 16 built-in specialists plus external coding agents (Claude Code, Codex, etc.) within projects with scheduling and connectors.
   Full card: https://gitnova.dev/en/r/Orkas-AI/Orkas.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-03 05:41 UTC, updated every 30 minutes.