# mochiiwuff/capri-desktop

> A desktop companion of Capri from Cyberpunk: Edgerunners 2 that lives on your screen and animatedly narrates what Claude Code is doing: edits, commands, permission requests and task completion.

- Magnitude: 5.6 out of 10 — Early signal
- Stars: 133 total · +12 stars measured 2026-10-26, 04:19–06:22 UTC, ≈ 92 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · Created: 2026-10-25 · Last push: 2026-10-26
- GitHub: https://github.com/mochiiwuff/capri-desktop · Page: https://gitnova.dev/en/r/mochiiwuff/capri-desktop

## Useful for

- Run Capri alongside Claude Code to see the current action in the ticker above her head
- Set up a permission-request alert from Claude via Capri teleporting to your cursor
- Disable the 'Possess my windows' option in the tray if the animation gets in the way

## Why it’s here

- Star-counter measurements on 2026-10-26 (UTC), 04:19–06:22: 121 → 133 stars (+12). This is the change over that interval.
- Estimated end-of-day forecast: about +92 stars, using observed gains and the previous day.
- The repository is 1 day old and already has 133 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #154.
- About 43 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: 20
- Issues and pull requests: 11
- Watchers: 4
- Average over the last week: 114 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 7
- Latest release: v0.3.1 (2026-10-26)

## Stars per day, last 2 days (oldest → newest, today is partial)

2026-10-25 … 2026-10-26: 135, 12

## Spotted in now

- Top new repositories this week: #154

## More in this category

1. **AgriciDaniel/claude-seo** — 8.2 · Breakout · AI agents · Python · +440 stars measured 2026-10-26, 00:11–06:22 UTC, ≈ 1,374 by evening
   SEO analysis plugin for Claude Code: 26 sub-skills and 19 agents run in parallel across technical SEO, E-E-A-T, Schema.org, GEO/AEO, local and international SEO, producing a prioritized action plan.
   Full card: https://gitnova.dev/en/r/AgriciDaniel/claude-seo.md
2. **makecindy/cindy** — 8.2 · Breakout · AI agents · TypeScript · +413 stars measured 2026-10-26, 00:11–06:22 UTC, ≈ 1,240 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
3. **TauricResearch/TradingAgents** — 7.6 · Breakout · AI agents · Python · +334 stars measured 2026-10-26, 00:12–06:22 UTC, ≈ 1,190 by evening
   A framework that simulates a trading firm with LLM agents (analysts, researchers, trader, risk manager) debating markets and producing trading decisions. Built for research, not real trading.
   Full card: https://gitnova.dev/en/r/TauricResearch/TradingAgents.md
4. **morganlinton/BeautifulRust** — 7.5 · Early signal · AI agents · Python · +156 stars measured 2026-10-26, 00:11–06:22 UTC, ≈ 570 by evening
   A Claude Code plugin with a rust-best-practices skill that teaches Claude to write idiomatic, robust Rust. The skill loads automatically whenever a task involves Rust, cargo, crates, the borrow checker, clippy, or .rs files.
   Full card: https://gitnova.dev/en/r/morganlinton/BeautifulRust.md
5. **microsoft/Agensh** — 7.4 · Early signal · AI agents · Python · +142 stars measured 2026-10-26, 00:12–06:22 UTC, ≈ 437 by evening
   A decentralized multi-agent harness in Python where agents discover and claim sub-tasks, share findings and asynchronously merge progress without a central orchestrator. It scales to 1,024 agents and targets tasks such as rebuilding…
   Full card: https://gitnova.dev/en/r/microsoft/Agensh.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 2026-10-26 06:33 UTC, updated every 30 minutes.