open-design vs scientific-agent-skills
The two are close in size: 102.7k stars for open-design, 53.1k for scientific-agent-skills. Over the days we have tracked them open-design moved +27.1% and scientific-agent-skills +68.6%, so scientific-agent-skills is growing faster right now.
open-design leads on context depth and customization. scientific-agent-skills does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
An open-source, local-first desktop alternative to closed design agents that turns local coding agents and a project's DESIGN.md into composable skills, plugins, and exportable real artifacts (HTML/PDF/PPTX/MP4).
- Stars
- 102.7k
- Tracked growth
- +27.1%
- Maturity
- ●●●●●
- Last commit
- 16m ago
- Language
- TypeScript
- License
- Apache-2.0
- Cost to run
- Your API key or Open Design Cloud (paid)
A large, curated collection of 148 domain-specific scientific Agent Skills with unified, provenance-rich access to 100+ scientific databases, packaged to plug into any Agent Skills–compatible host.
- Stars
- 53.1k
- Tracked growth
- +68.6%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- Python
- License
- MIT
- Cost to run
- Free to install; uses your API key(s)
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | open-design | scientific-agent-skills |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Project-wide access | ●●●●● Skills-only context |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● No noise controls | ●●●●● Docs guidance |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Plugins & design-system | ●●●●● Configurable skills |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Self-hostable |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Quickstart 3 commands | ●●●●● One-command install |
Which one to pick
Pick open-design if…
Local-first — run agent-native design workflows on your laptop with plugins and a DESIGN.md-driven design system, and export real files without relying on a single closed service.
- Context depth: Project-wide access (4/5 against 2/5)
- Customization: Plugins & design-system (5/5 against 3/5)
Pick scientific-agent-skills if…
Extensive scientific coverage — pick this when you need a maintained, ready-to-use library of validated skills and database connectors to turn your agent into a research assistant.
What people want from each one
nexu-io/open-design
Hacker News: Open Design: Use Your Coding Agent as a Design Engine drew 232 points and 92 comments.
K-Dense-AI/scientific-agent-skills
Questions people ask
Is open-design better than scientific-agent-skills?
open-design leads on context depth and customization. scientific-agent-skills does not take any axis by a clear margin. open-design is worth picking when local-first — run agent-native design workflows on your laptop with plugins and a DESIGN.md-driven design system, and export real files without relying on a single closed service.
Which of open-design and scientific-agent-skills keeps my code private?
open-design: Self-hostable (4/5). scientific-agent-skills: Self-hostable (4/5).
What does each one cost to run?
open-design: Your API key or Open Design Cloud (paid). scientific-agent-skills: Free to install; uses your API key(s).
Full profiles: nexu-io/open-design and K-Dense-AI/scientific-agent-skills. Everything else in Tools & MCP.