# b-nnett/grok-bot-0.18-reconstructed

> Unofficial source-oriented reconstruction of the Grok Bot 0.18.0 macOS app in TypeScript, adding an inference router (Cursor, Claude Code, Codex, OpenRouter) and a local Docker sandbox.

- Magnitude: 0.7 out of 10 — Steady
- Stars: 3,541 total · +2 stars measured 2026-10-29, 00:12–07:15 UTC, ≈ 5 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · Created: 2026-08-23 · Last push: 2026-08-23
- GitHub: https://github.com/b-nnett/grok-bot-0.18-reconstructed · Page: https://gitnova.dev/en/r/b-nnett/grok-bot-0.18-reconstructed

## Useful for

- Build a working macOS Grok Bot app from reconstructed sources via npm run bootstrap and package
- Switch the inference backend between Cursor, Claude Code, Codex and OpenRouter in Settings → Router
- Run the box host and execution daemon in a local Docker container instead of the remote sandbox

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:12–07:15: 3539 → 3541 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +5 stars, using observed gains and the previous day.
- The repository is archived — the author no longer develops it.

## 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: 3,657
- Issues and pull requests: 19
- Watchers: 19
- Average over the last week: 2 per day
- Usual pace: 2 per day
- Stars in the last hour (measured): 0

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 5, 8, 0, 4, 2, 0, 2, 0, 3, 1, 3, 2, 3, 1, 2, 0, 0, 1, 0, 1, 1, 2, 0, 1, 1, 3, 0, 1, 4, 2

## Magnitude by day, last 14 days

09-22 0.6, 09-23 0.6, 09-24 0.2, 09-25 0.4, 09-26 0.4, 09-27 0.2, 09-28 0.2, 09-29 0.4, 09-30 0.5, 10-01 0.9, 10-02 0.9, 10-27 0.2, 10-28 0.4, 10-29 0.7

## More in this category

1. **HKUDS/DeepTutor** — 8.9 · Breakout · AI agents · Python · +671 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 2,120 by evening
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **pbakaus/impeccable** — 8.0 · Breakout · AI agents · Rust · +904 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 2,767 by evening
   A set of commands and detector rules for AI coding agents that helps them produce better frontend design instead of generic templates. Installs as a skill into Claude Code, Cursor, Codex and other harnesses.
   Full card: https://gitnova.dev/en/r/pbakaus/impeccable.md
3. **elayadesign/ai-design-skills** — 7.9 · Breakout · AI agents · +365 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 1,330 by evening
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
4. **anonnerdfrenzy/survival-llm** — 7.7 · Early signal · AI agents · Python · +73 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 335 by evening
   A local offline LLM assistant with a library of ~1.5M survival, medical and how-to articles; every answer cites the exact source passage.
   Full card: https://gitnova.dev/en/r/anonnerdfrenzy/survival-llm.md
5. **makecindy/cindy** — 7.6 · Breakout · AI agents · TypeScript · +230 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 692 by evening
   Cindy is an open-source AI agent that combines multiple harnesses (Claude Code, Codex), models and tools into one agent working locally with your real files and apps. This repo is the client: Electron desktop and Expo/React Native mobile…
   Full card: https://gitnova.dev/en/r/makecindy/cindy.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 2026-10-29 07:17 UTC, updated every 30 minutes.