# InariNGT-Ofiicial/dsh-bili-humanism

> A DeepSeek Harness plugin that reads Bilibili subtitles and sampled frames and turns them into a private reflective journal, gradually building the agent's 'personality' in human-world.md. History, favorites, likes and coin writes are off by default and require manual authorization.

- Magnitude: 2.8 out of 10 — Early signal
- Stars: 115 total · +1 star measured 2026-10-24, 01:26–02:49 UTC, ≈ 17 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-10-20 · Last push: 2026-10-23
- GitHub: https://github.com/InariNGT-Ofiicial/dsh-bili-humanism · Page: https://gitnova.dev/en/r/InariNGT-Ofiicial/dsh-bili-humanism

## Useful for

- Install the local .tgz package and verify its SHA-256 before running
- Set up the daily 21:30 Beijing-time text capture
- Check transcript quality offline with probe and audio-profile

## Why it’s here

- Star-counter measurements on 2026-10-24 (UTC), 01:26–02:49: 114 → 115 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +17 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 115 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #199.
- About 7 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: 7
- Issues and pull requests: 7
- Watchers: 0
- Average over the last week: 26 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 2
- Latest release: v1.7.1 (2026-10-23)

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-20 … 2026-10-24: 0, 51, 44, 20, 1

## Spotted in now

- Top new repositories this week: #199

## More in this category

1. **aicodeking/leanrea** — 6.4 · Breakout · AI agents · Python · +28 stars measured 2026-10-24, 00:03–02:46 UTC, ≈ 390 by evening
   An 8 KB skill file for AI agents that replaces the REA MCP server: it tells the agent which CLI tools (asar, otool, nm, jadx, Ghidra, etc.) to use for reverse engineering and how to avoid common traps. Per the author's benchmark it is 38%…
   Full card: https://gitnova.dev/en/r/aicodeking/leanrea.md
2. **NVIDIA/OpenShell** — 6.2 · Breakout · AI agents · Rust · +84 stars measured 2026-10-24, 00:03–02:46 UTC, ≈ 787 by evening
   A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like Claude, Codex, OpenCode,…
   Full card: https://gitnova.dev/en/r/NVIDIA/OpenShell.md
3. **JoasASantos/REA-Prompts** — 5.9 · Peaking · AI agents · +30 stars measured 2026-10-24, 00:03–02:47 UTC, ≈ 248 by evening
   A curated collection of prompts for using REA (Reverse Engineer Anything) with AI coding agents to inspect binaries, firmware, kernels, games, APKs, Electron apps and websites. Covers installation, feature tracing, cloning, vulnerability…
   Full card: https://gitnova.dev/en/r/JoasASantos/REA-Prompts.md
4. **Graphify-Labs/graphify** — 5.0 · Steady · AI agents · Python · +39 stars measured 2026-10-24, 00:03–02:47 UTC, ≈ 575 by evening
   Turns any codebase, docs, SQL schemas, configs, and PDFs into a queryable knowledge graph. Works as a /graphify skill in Claude Code, Cursor, Codex, and Gemini CLI with local deterministic AST parsing.
   Full card: https://gitnova.dev/en/r/Graphify-Labs/graphify.md
5. **morluto/rea** — 4.8 · Cooling · AI agents · TypeScript · +470 stars measured 2026-10-24, 00:03–02:47 UTC, ≈ 5,060 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.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 2026-10-24 02:57 UTC, updated every 30 minutes.