Turn any Agent Skill (SKILL.md) into a callable API via POST /run . Multi-model, stateful, open source. Quick Start npm install -g @skrun-dev/cli # Import an existing skill → deploy → call skrun init --from-skill ./my-skill skrun deploy curl -X POST localhost:4000/api/agents/dev/my-skill/run \ -H " Authorization: Bearer <token> " \ -H " Content-Type: application/json " \ -d ' {"input": {"query": "analyze this"}} ' Get Started Create a new agent Import an existing skill Develop & test locally Deploy Create a new agent skrun init my-agent cd my-agent # Creates SKILL.md (instructions) + agent.yaml (config) Import an existing skill skrun init --from-skill ./path-to-skill # Reads SKILL.md, asks 2-3 questions, generates agent.yaml Develop locally skrun dev # ✓ Server running at http://localhost:3000 # POST /run ready — watching for changes... skrun test # ✓ basic-test (output.score >= 0) # 1 passed, 0 failed Deploy skrun deploy # ✓ Validated → Built → Pushed # 🚀 POST http://localhost:4000/api/agents/you/my-agent/run v0.1 ships with a local runtime. Cloud deploy is on the roadmap — the architecture is ready ( RuntimeAdapter interface). Key Concepts Agent Skills — SKILL.md standard, compatible with Claude Code, Copilot, Codex agent.yaml — Runtime config: model, inputs/outputs, permissions, state, tests POST /run — Every agent is an API. Typed inputs, structured outputs. Multi-model — Anthropic, OpenAI, Google, Mistral, Groq with automatic fallback Stateful — Agents remember across runs via key-value state Tool calling — Two approaches: CLI tools ( scripts/ — write your own, bundled with the agent) and MCP servers ( npx — standard ecosystem , same as Claude Desktop) Demo Agents All examples use Google Gemini Flash by default. Change the model section in agent.yaml to use any supported provider . Agent What it shows code-review Import a skill, get a code quality API pdf-processing Tool calling with local scripts seo-audit Stateful — run twice, it remembers and compares data-analyst Typed I/O — CSV in, structured insights out email-drafter Business use case — non-dev API consumer web-scraper MCP server — headless browser via @playwright/mcp Try an example # 1. Start the registry cp .env.example .env # add your GOOGLE_API_KEY pnpm dev:registry # keep this terminal open # 2. In another terminal skrun login --token dev-token cd examples/code-review skrun build && skrun push # 3. Call the agent curl -X POST http://localhost:4000/api/agents/dev/code-review/run \ -H " Authorization: Bearer dev-token " \ -H " Content-Type: application/json " \ -d ' {"input": {"code": "function add(a,b) { return a + b; }"}} ' Windows (PowerShell): use curl.exe instead of curl , and use @input.json for the body. CLI Command Description skrun init [dir] Create a new agent skrun init --from-skill <path> Import existing skill skrun dev Local server with POST /run skrun test Run agent tests skrun build Package .agent bundle skrun deploy Build + push + live URL skrun push / pull Registry upload/download skrun login / logout Authentication skrun logs <agent> Execution logs Full CLI reference → Documentation agent.yaml specification CLI reference Contributing Contributing git clone https://github.com/skrun-dev/skrun.git cd skrun pnpm install && pnpm build && pnpm test See CONTRIBUTING.md for conventions and setup. License MIT