modlens is a skill AI agent for Enable AI coding assistants to interpret image inputs and generate structured code or insights based on visual content. Pricing: Free. As of 2026-10-22, KanonAgent records 3.0k upvotes. First indexed by KanonAgent on 2026-08-15.
Modlens is a vision plugin for DeepSeek Harness that turns images like UI screenshots and charts into structured JSON by analyzing text, layout, and meaning.
3.0k upvotes
Tracked by Kanon since Aug 15, 2026
Status basis: npm_downloads_7d momentum fell to -6561 per 3d from 1558 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -6561 per 3d from 1558 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -6561 per 3d from 2211 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 4206 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1558 per 3d from 5396 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 1558 per 3d from 5396 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 2211 in the last 3d vs 731 in the 3d before (ratio 3.0x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 731 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -4012 per 3d from 940 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -4012 per 3d from 1065 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 655 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 940 in the last 3d vs 590 in the 3d before (ratio 1.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 655 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 1065 in the last 3d vs 465 in the 3d before (ratio 2.3x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to -285 per 3d from 1288 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 413 per 3d from 5576 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -1030 per 3d from 6695 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 914 per 3d from 4662 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 5576 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 914 per 3d from 4662 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 6695 in the last 3d vs 120 in the 3d before (ratio 55.8x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 4662 in the last 3d vs 1302 in the 3d before (ratio 3.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 1492 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 4662 in the last 3d vs 1302 in the 3d before (ratio 3.6x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 1492 (<= 40% of the prior window)
🔎 Known / Unknown
16 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🚀 Breakout logappend-only · timestamped
2026-08-17GitHubflagged at 462 stars/day → now ⭐4.0k
Full breakout log →🤖 Agent teardown · skill
Job to be doneEnable AI coding assistants to interpret image inputs and generate structured code or insights based on visual content.
Who it is forDevelopers and AI tool builders working with visual data in code generation or analysis workflows.
Prerequisitesopen source
PricingFree
Traction · why it is risingGained 536 votes on ProductHunt, indicating strong early interest from developer communities.
Why it matters
It fills a critical gap in AI agents by adding visual understanding, making it a foundational component for multimodal AI workflows.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“The FIRST vision plugin for DeepSeek Harness (dsh)”— readme
“one command, `npx -y @deepseek-ai/dsh plugin --profile web add @liustack/[email protected]`”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building modlens? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is modlens?
Modlens is a vision plugin for DeepSeek Harness that turns images like UI screenshots and charts into structured JSON by analyzing text, layout, and meaning.
What does modlens do?
Enable AI coding assistants to interpret image inputs and generate structured code or insights based on visual content.
Why does modlens matter?
It fills a critical gap in AI agents by adding visual understanding, making it a foundational component for multimodal AI workflows.
How much does modlens cost?
Free
Is modlens free?
Yes — modlens has a free tier. Pricing as stated on its own page: Free
Is modlens open source?
Yes — modlens is open source.
How popular is modlens?
As tracked by KanonAgent: 3.0k upvotes (first indexed 2026-08-15).
When did modlens take off?
KanonAgent flagged modlens as breaking out on 2026-08-17 on GitHub (at 462 stars/day that moment). The breakout log is append-only: https://kanonagent.com/rising
What are the best modlens alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, archify, open-design, deer-flow, ruflo, career-ops.