# Lniosy/souhun

> A desktop tool for Mac and Windows that lists, writes, and forgets the memories of Grok Bots through the already logged-in account, without touching local files or tokens. It marks each memory as account-wide, bot-only, team, or unlabeled.

- Magnitude: 4.9 out of 10 — Early signal
- Stars: 160 total · +3 stars measured 2026-11-04, 03:12–03:55 UTC, ≈ 43 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Swift · License: MIT · Created: 2026-11-02 · Last push: 2026-11-02
- GitHub: https://github.com/Lniosy/souhun · Page: https://gitnova.dev/en/r/Lniosy/souhun

## Useful for

- List all bots of an account and pull their current memories for review
- Write a new memory and choose whether it is account-wide or bot-only
- Forget an existing memory by exact text through the selected bot

## Why it’s here

- Star-counter measurements on 2026-11-04 (UTC), 03:12–03:55: 157 → 160 stars (+3). This is the change over that interval.
- Estimated end-of-day forecast: about +43 stars, using observed gains and the previous day.
- The repository is 2 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.
- Top new repositories this week: #198.
- About 18 forks a day — people are taking the code.
- Recent forks include notable developers: @harry1080 (307 followers).

## 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: 44
- Issues and pull requests: 0
- Watchers: 1
- Average over the last week: 68 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 3
- Latest release: v1.0.0 (2026-11-02)

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-11-02 … 2026-11-04: 105, 55, 3

## Spotted in now

- Top new repositories this week: #198

## More in this category

1. **storytold/craft-anything** — 9.0 · Breakout · AI agents · Rust · +521 stars measured 2026-11-04, 00:17–03:55 UTC, ≈ 3,345 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** — 9.0 · Breakout · AI agents · Rust · +441 stars measured 2026-11-04, 00:17–03:55 UTC, ≈ 2,311 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. **KKKKhazix/agent-autoloop** — 8.6 · Early signal · AI agents · TypeScript · +734 stars measured 2026-11-04, 01:02–03:55 UTC, ≈ 1,984 by evening
   A lightweight scheduler for CLI agents (Claude Code, Codex, etc.): runs them in the background on events and schedules, and sends a card to a messenger or desktop when a decision is needed. Runs locally on Mac or Linux with no cloud and…
   Full card: https://gitnova.dev/en/r/KKKKhazix/agent-autoloop.md
4. **pingdotgg/t3code** — 8.5 · Breakout · AI agents · TypeScript · +340 stars measured 2026-11-04, 00:17–03:55 UTC, ≈ 2,050 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
5. **ccch1mneyyy/dsh-Go** — 8.3 · Breakout · AI agents · Dart · +499 stars measured 2026-11-04, 00:17–03:55 UTC, ≈ 2,021 by evening
   Unofficial Android client for DeepSeek Harness: runs DSH on the phone in a built-in Linux environment without root or Termux, and can also remotely control DSH on your computer.
   Full card: https://gitnova.dev/en/r/ccch1mneyyy/dsh-Go.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 2026-11-04 04:07 UTC, updated every 30 minutes.