# lcoutodemos/chums

> Chums brings the Claude Code and Codex agents already running on your Mac to an Apple Watch and iPhone, where each agent is a character acting out its state. You speak a task, watch tool calls, and approve or deny actions.

- Magnitude: 1.6 out of 10 — Steady
- Stars: 112 total · +2 stars measured 2026-10-18, 17:56–20:05 UTC, ≈ 3 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Swift · License: Apache-2.0 · Created: 2026-10-13 · Last push: 2026-10-13
- GitHub: https://github.com/lcoutodemos/chums · Homepage: https://chums.club · Page: https://gitnova.dev/en/r/lcoutodemos/chums

## Useful for

- Send a voice task to an agent from the Apple Watch without opening the Mac
- Approve or deny an agent's permission request right from the watch
- Switch between several agents and read their replies on the iPhone

## Why it’s here

- Star-counter measurements on 2026-10-18 (UTC), 17:56–20:05: 110 → 112 stars (+2). This is the change over that interval.
- Estimated end-of-day forecast: about +3 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 112 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #198.

## 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: 13
- Issues and pull requests: 0
- Watchers: 0
- 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 6 days (oldest → newest, today is partial)

2026-10-13 … 2026-10-18: 34, 9, 7, 24, 14, 2

## Spotted in now

- Top new repositories this week: #198

## More in this category

1. **google-research/harness2** — 9.3 · Breakout · AI agents · Python · +3,858 stars measured 2026-10-18, 02:46–20:00 UTC, ≈ 4,506 by evening
   A framework for recursive optimization of AI agent harnesses (prompts, tools, memory, skills) without fine-tuning model weights, with JobBench, LAB and WorkBuddy-Bench benchmarks.
   Full card: https://gitnova.dev/en/r/google-research/harness2.md
2. **MadsLorentzen/ai-job-search** — 8.0 · Breakout · AI agents · Python · +2,217 stars measured 2026-10-18, 00:21–20:00 UTC, ≈ 2,623 by evening
   A job application framework built on Claude Code: evaluates postings, tailors CVs, and writes cover letters. Runs locally, focused on the Danish job market.
   Full card: https://gitnova.dev/en/r/MadsLorentzen/ai-job-search.md
3. **anthropics/claude-plugins-official** — 7.8 · Breakout · AI agents · Python · +813 stars measured 2026-10-18, 00:21–20:00 UTC, ≈ 972 by evening
   Official Anthropic-managed directory of Claude Code plugins: internal plugins plus third-party ones from partners, installable via the built-in marketplace.
   Full card: https://gitnova.dev/en/r/anthropics/claude-plugins-official.md
4. **anomalyco/opencode** — 7.7 · Breakout · AI agents · TypeScript · +1,105 stars measured 2026-10-18, 00:21–20:00 UTC, ≈ 1,313 by evening
   Open source AI coding agent with terminal and desktop interfaces. Ships with a build agent (full edit and command access) and a read-only plan agent for code analysis.
   Full card: https://gitnova.dev/en/r/anomalyco/opencode.md
5. **android/skills** — 6.8 · Breakout · AI agents · Kotlin · +285 stars measured 2026-10-18, 00:21–20:00 UTC, ≈ 340 by evening
   A repository of AI-optimized modular instructions (SKILL.md) that help agents follow Android development best practices from developer.android.com. Installed via Android CLI or as a plugin for Claude Code and Codex.
   Full card: https://gitnova.dev/en/r/android/skills.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 2026-10-18 20:10 UTC, updated every 30 minutes.