TypeScript · MIT
liustack/modlens
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。
★ 4.8k
Stars
150 forks · 4 open issues
+23/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
51.3
Momentum / 100
see the breakdown below
8mo ago
Created
last push 15d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 26.3 | +23/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.4 | last week ran 1.03× the monthly pace |
| Freshness | 15 | 13.9 | last push 15d ago; decays to zero at 180 days |
| Scale | 15 | 10.7 | 4.8k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 51.3 | sum of the above |
Detail
| Topics | agent-skillsclaude-codeclaude-skillscodexcordisdeepseekdshdsh-pluginglmharnessharness-engineeringhermes-agentimage-to-textmultimodalocropenclawpi-agenttext-only-llmvisionvision-transformer |
| Matched on | Agent Skills & MCP (agent-skills) |
| Short window | +159 stars over 7 days = 22.7/day |
| Long window | +576 stars over 26 days = 22.2/day |
| Lifetime average | 18.63 stars/day over 256 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |