# bowenliang123/dsh-context

> A DeepSeek Harness plugin that visualizes an agent's context: dashboard, browser, sidebar panel and /context command showing composition, stats and evolution of the context window.

- Magnitude: 2.2 out of 10 — Steady
- Stars: 2,351 total · +8 stars measured 2026-10-19, 12:13–13:52 UTC, ≈ 20 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: Apache-2.0 · Created: 2026-08-14 · Last push: 2026-10-19
- GitHub: https://github.com/bowenliang123/dsh-context · Homepage: https://www.npmjs.com/package/dsh-context · Page: https://gitnova.dev/en/r/bowenliang123/dsh-context

## Useful for

- Inspect what the current context window is made of and which part takes the most tokens
- Track context growth per request and see when auto-compaction kicks in
- Compare token usage and cost across sessions over 7 or 30 days

## Why it’s here

- Star-counter measurements on 2026-10-19 (UTC), 12:13–13:52: 2343 → 2351 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +20 stars, using observed gains and the previous day.
- GitHub Trending TypeScript today: #15, +65 stars.

## 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: 73
- Issues and pull requests: 158
- Watchers: 9
- Average over the last week: 42 per day
- Usual pace: 26 per day
- Stars in the last hour (measured): 6
- Latest release: v0.73.3 (2026-10-19)

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

2026-09-20 … 2026-10-19: 18, 16, 12, 21, 14, 5, 12, 10, 13, 24, 161, 49, 17, 23, 17, 18, 14, 25, 23, 30, 15, 38, 46, 38, 48, 44, 33, 56, 53, 8

## Spotted in now

- GitHub Trending TypeScript today: #15, +65 stars

## More in this category

1. **google-research/harness2** — 9.6 · Breakout · AI agents · Python · +3,667 stars measured 2026-10-19, 00:05–13:45 UTC, ≈ 6,240 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** — 9.3 · Breakout · AI agents · Python · +2,540 stars measured 2026-10-19, 00:05–13:45 UTC, ≈ 4,182 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. **anomalyco/opencode** — 8.3 · Breakout · AI agents · TypeScript · +728 stars measured 2026-10-19, 00:05–13:45 UTC, ≈ 1,250 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
4. **alchaincyf/huashu-motion** — 7.6 · Early signal · AI agents · JavaScript · +516 stars measured 2026-10-19, 00:05–13:45 UTC, ≈ 831 by evening
   A skill for coding agents (Claude Code, Codex) that turns a product description into code-driven animated launch films, composes music, and opens a browser editor for frame-level edits.
   Full card: https://gitnova.dev/en/r/alchaincyf/huashu-motion.md
5. **finereli/whatsapp-mcp** — 7.2 · Early signal · AI agents · TypeScript · +220 stars measured 2026-10-19, 00:13–13:45 UTC, ≈ 334 by evening
   A read-only MCP server on Cloudflare Workers that lets your AI agent search and read your own WhatsApp messages. Your phone stays the source of truth; the server acts as a linked device and cannot send anything.
   Full card: https://gitnova.dev/en/r/finereli/whatsapp-mcp.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 2026-10-19 14:01 UTC, updated every 30 minutes.