skrun-dev

skrun-dev / skrun

Public

Deploy any Agent Skill as an API via POST /run. Multi-model, stateful, open source.

skrun.sh agent-skills ai-agents api cli llm
39
4
100% credibility
Found Apr 09, 2026 at 39 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

Skrun transforms AI agent skill instructions into deployable web services with local testing, a sharing registry, and easy API calls.

How It Works

1
🔍 Discover Skrun

You hear about a simple way to turn your AI helper instructions into a ready-to-use web service anyone can call.

2
✨ Create your agent

Pick a name and description for your helper, connect a smart AI brain, and describe what inputs it needs.

3
🧪 Test and tweak locally

Run a pretend server on your computer to chat with your helper, check it works, and fix any issues right away.

4
🚀 Share it online

Package everything up and send it to the shared collection with one easy action.

5
📞 Call your helper anytime

Send simple messages to your live helper from anywhere, like a phone call to get instant smart answers.

🎉 Your AI helper is live!

Now anyone can use your creation through a web address, remembering past chats and delivering reliable results every time.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 39 to 39 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is skrun?

Skrun turns any Agent Skill—those SKILL.md files from Claude or Copilot—into a production-ready API via a single POST /run endpoint. You get multi-model support across Anthropic, OpenAI, Google, and more, plus stateful memory and tool calling for scripts or MCP servers. TypeScript CLI handles init from existing skills, local dev server, testing, bundling, and deploy—deploy anything from GitHub locally or to cloud via Azure in minutes.

Why is it gaining traction?

It slashes deploy friction: no infra setup, just skrun deploy for a live endpoint you can hit anytime. Multi-LLM fallback and structured I/O beat raw API wrappers, while local runtime means deploy GitHub repos to servers or Hostinger without vendor lock-in. Devs dig the bundle format for GitHub Actions or pages deploys.

Who should use this?

AI builders shipping agent prototypes as APIs, like SEO auditors or data analysts needing quick endpoints. Ideal for teams deploying GitHub Actions runners or io pages, or ops folks handling AnyDesk deploys via Intune/GPO who want agent skills online fast.

Verdict

Promising for local dev and easy deploys (39 stars), but 1.0% credibility signals early maturity—docs are crisp, tests solid, yet cloud hosting's roadmap. Try for prototypes; monitor for prod.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.