@agentskit/runtime

@agentskit/runtime

Run autonomous agents in 5 lines — no UI, no boilerplate, just results.

Tags: ai · agents · llm · agentskit · openai · anthropic · ai-agents · autonomous-agents · react-loop · orchestration · multi-agent

How this fits the ecosystem

@agentskit/runtime is the headless agent engine: ReAct loops, tools, skills, delegation, memory, cancellation, and structured run results.

• AgentsKit: compose it with the other packages in this repo to build agents from small, swappable parts.
• Registry: look for ready agents and templates that already use this layer at registry.agentskit.io.
• Playbook: learn the production patterns behind this layer at playbook.agentskit.io.
• AKOS: run the same concepts with enterprise deployment, governance, and observability at akos.agentskit.io.

Docs: package guide · agent handoff

Why runtime

• ReAct loop handled for you — observe, think, act, repeat: the runtime drives the full cycle and stops when the agent decides it's done
• Structured, inspectable results — every run returns the final content, step count, all tool calls made, and total duration; no black boxes
• Production-ready lifecycle — lazy tool init/dispose, AbortSignal cancellation, memory persistence, and AgentEvent emissions for observability
• Multi-agent delegation — pass a planner skill with named delegates and the runtime coordinates sub-agents automatically

Install

npm install @agentskit/runtime @agentskit/adapters

Quick example

import { createRuntime } from '@agentskit/runtime'
import { openai } from '@agentskit/adapters'
import { webSearch, filesystem } from '@agentskit/tools'

const runtime = createRuntime({
  adapter: openai({ apiKey: process.env.OPENAI_API_KEY, model: 'gpt-4o' }),
  tools: [webSearch(), ...filesystem({ basePath: './workspace' })],
  systemPrompt: 'You are a helpful research assistant.',
})

const result = await runtime.run('Research the latest advances in quantum computing')
console.log(result.content)
console.log(`Completed in ${result.steps} steps, ${result.durationMs}ms`)

With skills

import { createRuntime } from '@agentskit/runtime'
import { anthropic } from '@agentskit/adapters'
import { researcher } from '@agentskit/skills'

const runtime = createRuntime({
  adapter: anthropic({ apiKey: process.env.ANTHROPIC_API_KEY!, model: 'claude-sonnet-4-6' }),
})

const result = await runtime.run('Summarize REST vs GraphQL', { skill: researcher })
console.log(result.content)

Features

• createRuntime — single entry point for headless agent execution.
• ReAct loop: observe → think → act → repeat until done.
• Returns { content, steps, toolCalls, durationMs } — fully inspectable.
• AbortSignal cancellation support.
• Tool init / dispose lifecycle hooks.
• AgentEvent emissions for observability integrations.
• retriever option for RAG context injection.

Advanced primitives

Primitive	Purpose	Docs
createDurableRunner + createFileStepLog	Temporal-style step log; resume on crash	Durable execution
supervisor / swarm / hierarchical / blackboard	Ready-made multi-agent topologies	Topologies
speculate	Fan-out N adapters, race + abort losers	Speculative execution
createCronScheduler + createWebhookHandler	Background agents, cron + webhooks	Background agents

Ecosystem

Package	Role
@agentskit/core	createRuntime contracts, Retriever
@agentskit/adapters	LLM adapters
@agentskit/tools	Tool modules
@agentskit/skills	Pre-built skills
@agentskit/rag	retriever for context injection

Contributors

License

MIT — see LICENSE.

Docs

Full documentation · GitHub