# yjh051108/dsh-routing-suite

> A DSH (DeepSeek Harness) plugin suite: a runtime injector, a reasoning-mode routing preset, and a two-level task protocol with auditing. It manages agent behavior across long sessions.

- Magnitude: 0.9 out of 10 — Steady
- Stars: 7,002 total · +0 stars measured 2026-10-29, 00:12–03:02 UTC, ≈ 4 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: JavaScript · License: MIT · Created: 2026-08-14 · Last push: 2026-09-18
- GitHub: https://github.com/yjh051108/dsh-routing-suite · Page: https://gitnova.dev/en/r/yjh051108/dsh-routing-suite

## Useful for

- Install the injector and router-standard preset to route tasks by reasoning mode
- Run node scripts/measure.mjs on your session.jsonl to compute model attention metrics
- Enable graded mode for a step-by-step task protocol with check-ins and final verification

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:12–03:02: 7002 → 7002 stars (+0). This is the change over that interval.
- Estimated end-of-day forecast: about +4 stars, using observed gains and the previous day.

## 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: 194
- Issues and pull requests: 247
- Watchers: 15
- Average over the last week: 5 per day
- Usual pace: 7 per day
- Stars in the last hour (measured): 0
- Latest release: 0.0.1-rc1 (2026-09-02)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 7, 6, 7, 10, 1, 7, 10, 6, 5, 9, 5, 9, 5, 8, 8, 4, 3, 4, 9, 6, 6, 8, 5, 7, 6, 6, 5, 5, 5, 0

## Magnitude by day, last 14 days

10-16 1.1, 10-17 0.9, 10-18 1.3, 10-19 1.8, 10-20 1.5, 10-21 1.1, 10-22 1.2, 10-23 1.2, 10-24 1.4, 10-25 1.1, 10-26 1.2, 10-27 1.0, 10-28 1.0, 10-29 1.0

## More in this category

1. **HKUDS/DeepTutor** — 8.7 · Breakout · AI agents · Python · +259 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 1,727 by evening
   A lifelong personalized AI tutor with long-term memory: builds learning paths, reads documents and books, and runs practice and assessments via a multi-agent system and RAG.
   Full card: https://gitnova.dev/en/r/HKUDS/DeepTutor.md
2. **elayadesign/ai-design-skills** — 7.9 · Breakout · AI agents · +170 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 1,292 by evening
   A collection of markdown-based design skills for AI coding tools like Claude Code, Cursor, Codex and Windsurf, covering landing page design and turning static designs into animated showcases.
   Full card: https://gitnova.dev/en/r/elayadesign/ai-design-skills.md
3. **anonnerdfrenzy/survival-llm** — 7.7 · Early signal · AI agents · Python · +29 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 354 by evening
   A local offline LLM assistant with a library of ~1.5M survival, medical and how-to articles; every answer cites the exact source passage.
   Full card: https://gitnova.dev/en/r/anonnerdfrenzy/survival-llm.md
4. **unclebob/ub-mode** — 7.6 · Breakout · AI agents · +134 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 1,077 by evening
   An agent skill that enforces disciplined software engineering practices when writing or changing code: TDD, root-cause fixes, behavior testing, and quality gates via mutation testing. Installed as SKILL.md into the agent's skills directory.
   Full card: https://gitnova.dev/en/r/unclebob/ub-mode.md
5. **CopilotKit/OpenDuet** — 7.6 · Early signal · AI agents · TypeScript · +35 stars measured 2026-10-29, 00:02–02:52 UTC, ≈ 556 by evening
   A self-hosted proactive AI agent built on OpenBot and CopilotKit: it starts work on its own, runs in its own browser, and asks for approval before acting.
   Full card: https://gitnova.dev/en/r/CopilotKit/OpenDuet.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 2026-10-29 03:04 UTC, updated every 30 minutes.