skelm — agentic workflows you can actually ship to production

One authoring model from scripts to durable agents.

A workflow is a typed TypeScript module. Use deterministic code, model inference, and agent loops directly, then host the same workflow through the gateway when it needs schedules, webhooks, queues, or durable state.

A real workflow, end to end

Incident response from the current examples: parallel deterministic triage, then an agent step with explicit tools, MCP, filesystem, and network permissions.

import { agent, code, parallel, pipeline } from 'skelm'
import { z } from 'zod'

export default pipeline({
  id: 'incident-response',
  input: z.object({
    incidentId: z.string(),
    service: z.string(),
    description: z.string(),
  }),
  output: z.object({
    rootCause: z.string(),
    immediateActions: z.array(z.string()),
  }),
  triggers: [{ kind: 'webhook', path: '/webhooks/incident' }],
  steps: [
    parallel({
      id: 'triage',
      steps: [
        code({ id: 'search-issues', run: () => ({ issues: [] }) }),
        code({ id: 'open-channel', run: () => ({ channel: 'inc-001' }) }),
      ],
    }),
    agent({
      id: 'root-cause',
      backend: 'opencode',
      prompt: (ctx) => `Analyze this incident:\n${ctx.input.description}`,
      permissions: {
        allowedTools: ['gh.search_issues', 'slack.post_message'],
        allowedMcpServers: ['github'],
        allowedExecutables: [],
        fsRead: [],
        fsWrite: [],
        networkEgress: { allowHosts: ['api.github.com', 'slack.com'] },
      },
      output: z.object({
        rootCause: z.string(),
        immediateActions: z.array(z.string()),
      }),
      maxTurns: 4,
    }),
  ],
})