# DIYgod/pinky

> Pinky lets AI agents (Claude Code, Codex, Cursor, etc.) operate a real iPhone or Android phone over MCP while you watch from your computer and approve risky steps. Pinky's gateway enforces approvals for payments, transfers and other risky actions, and banking and wallet apps are hidden from agents by default.

- Magnitude: 7.6 out of 10 — Early signal
- Stars: 830 total · +47 stars measured 2026-11-09, 00:02–01:27 UTC, ≈ 627 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Go · License: Apache-2.0 · Created: 2026-11-06 · Last push: 2026-11-08
- GitHub: https://github.com/DIYgod/pinky · Page: https://gitnova.dev/en/r/DIYgod/pinky

## Useful for

- Have an agent place an order in an app while you approve the payment manually
- Connect Claude Code to an Android emulator and run a phone workflow end to end
- Record the screen and export an HTML report of the agent's actions on the phone

## Why it’s here

- Star-counter measurements on 2026-11-09 (UTC), 00:02–01:27: 783 → 830 stars (+47). This is the change over that interval.
- Estimated end-of-day forecast: about +627 stars, using observed gains and the previous day.
- The repository is 3 days old and already has 830 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #19.
- About 129 forks a day — people are taking the code.

## 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: 68
- Issues and pull requests: 24
- Watchers: 2
- Average over the last week: 366 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 33
- Latest release: v2026.1109.7 (2026-11-08)

## Stars per day, last 4 days (oldest → newest, today is partial)

2026-11-06 … 2026-11-09: 0, 220, 617, 47

## Magnitude by day, last 2 days

11-08 7.5, 11-09 7.6

## Spotted in now

- Top new repositories this week: #19

## More in this category

1. **JuneYaooo/rea-video** — 7.3 · Breakout · AI agents · Python · +75 stars measured 2026-11-09, 00:02–01:27 UTC, ≈ 764 by evening
   A skill for AI coding agents that reverse-engineers any video shot by shot, identifying whether each shot is live-action, AI-generated, 3D, or code-driven, and producing a replication plan.
   Full card: https://gitnova.dev/en/r/JuneYaooo/rea-video.md
2. **vercel-labs/agent-browser** — 7.0 · Breakout · AI agents · Rust · +69 stars measured 2026-11-09, 00:02–01:28 UTC, ≈ 635 by evening
   A Rust CLI for browser automation aimed at AI agents: it opens pages, clicks elements, fills forms, and takes screenshots via simple commands.
   Full card: https://gitnova.dev/en/r/vercel-labs/agent-browser.md
3. **lxe/phoneuse** — 6.3 · Early signal · AI agents · C · +16 stars measured 2026-11-09, 00:02–01:28 UTC, ≈ 235 by evening
   Tool to see and operate an unmodified iPhone from a Linux PC: screen arrives over AirPlay while the PC acts as a Bluetooth mouse and keyboard. Includes a CLI and MCP server for agents.
   Full card: https://gitnova.dev/en/r/lxe/phoneuse.md
4. **ranxianglei/billion-context** — 5.5 · Breakout · AI agents · TypeScript · +59 stars measured 2026-11-09, 00:02–01:28 UTC, ≈ 488 by evening
   A context-compression proxy plugin between a coding agent and the model API: folds conversation history into layered summaries, saves tokens, and lets a single session run for months within a small context window.
   Full card: https://gitnova.dev/en/r/ranxianglei/billion-context.md
5. **storytold/craft-anything** — 5.3 · Peaking · AI agents · Rust · +143 stars measured 2026-11-09, 00:02–01:28 UTC, ≈ 1,477 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

---

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 2026-11-09 01:38 UTC, updated every 30 minutes.