ai-sdk-agents

@BjornMelin/ai-sdk-agents

0 forks

Updated 4/1/2026

Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep, callOptionsSchema/prepareCall, dynamic tool selection, tool loops, or agent workflows (sequential, routing, evaluator-optimizer, orchestrator-worker). Triggers: ToolLoopAgent, agent loop, stopWhen, stepCountIs, prepareStep, callOptionsSchema, prepareCall, hasToolCall, InferAgentUIMessage, agent workflows.

Installation

$npx agent-skills-cli install @BjornMelin/ai-sdk-agents

Claude Code

Cursor

Copilot

Codex

Antigravity

Details

RepositoryBjornMelin/dev-skills

Pathskills/ai-sdk-agents/SKILL.md

Branchmain

Scoped Name@BjornMelin/ai-sdk-agents

Usage

After installing, this skill will be available to your AI coding assistant.

Verify installation:

npx agent-skills-cli list

Skill Instructions

name: ai-sdk-agents description: | Expert guidance for building AI agents with ToolLoopAgent (AI SDK v6+). Use when creating agents, configuring stopWhen/prepareStep, callOptionsSchema/prepareCall, dynamic tool selection, tool loops, or agent workflows (sequential, routing, evaluator-optimizer, orchestrator-worker). Triggers: ToolLoopAgent, agent loop, stopWhen, stepCountIs, prepareStep, callOptionsSchema, prepareCall, hasToolCall, InferAgentUIMessage, agent workflows.

AI SDK Agents

Build autonomous agents with ToolLoopAgent: reusable model + tools + loop control.

Quick Start

Assume Zod v4.3.5 for schema typing.

import { ToolLoopAgent, tool } from 'ai';
import { anthropic } from '@ai-sdk/anthropic';
import { z } from 'zod';

const weatherAgent = new ToolLoopAgent({
  model: anthropic('claude-sonnet-4-20250514'),
  tools: {
    weather: tool({
      description: 'Get the weather in a location (F)',
      inputSchema: z.object({ location: z.string() }),
      execute: async ({ location }) => ({ location, temperature: 72 }),
    }),
  },
});

const result = await weatherAgent.generate({
  prompt: 'What is the weather in San Francisco?',
});

When to Use ToolLoopAgent vs Core Functions

Use ToolLoopAgent for dynamic, multi-step tasks where the model decides which tools to call.
Use generateText/streamText for deterministic flows or strict ordering.

Essential Patterns

Structured Output

import { ToolLoopAgent, Output } from 'ai';
import { z } from 'zod';

const analysisAgent = new ToolLoopAgent({
  model: 'openai/gpt-4o',
  output: Output.object({
    schema: z.object({
      sentiment: z.enum(['positive', 'neutral', 'negative']),
      summary: z.string(),
    }),
  }),
});

Streaming Agent

const stream = myAgent.stream({ prompt: 'Summarize this report' });
for await (const chunk of stream.textStream) {
  process.stdout.write(chunk);
}

API Route

import { createAgentUIStreamResponse } from 'ai';

export async function POST(request: Request) {
  const { messages } = await request.json();
  return createAgentUIStreamResponse({ agent: myAgent, messages });
}

Type-Safe Client Integration

import { ToolLoopAgent, InferAgentUIMessage } from 'ai';

const myAgent = new ToolLoopAgent({ model, tools });
export type MyAgentUIMessage = InferAgentUIMessage<typeof myAgent>;

Loop Control Checklist

Set stopWhen (default: stepCountIs(20)) for safety.
Use hasToolCall('finalAnswer') to stop on terminal actions.
Use prepareStep to swap models, compress messages, or limit tools per step.

Runtime Configuration

Use callOptionsSchema to define type-safe runtime options.
Use prepareCall to select model/tools or inject RAG context once per call.
Use prepareStep for per-step decisions (budget limits, dynamic tools).

Reference Files

Reference	When to Use
`references/fundamentals.md`	ToolLoopAgent basics, Output types, streaming
`references/loop-control.md`	stopWhen, hasToolCall, prepareStep patterns
`references/configuration.md`	callOptionsSchema, prepareCall vs prepareStep
`references/workflow-patterns.md`	multi-agent workflows and routing
`references/real-world.md`	RAG, multimodal, file processing
`references/production.md`	monitoring, safety, cost control
`references/migration.md`	v6 migration notes

More by BjornMelin

View all

vitest-dev

World-class Vitest QA/test engineer for TypeScript + Next.js (local + CI performance focused)

zod-v4

Expert guidance for Zod v4 schema validation in TypeScript. Use when designing schemas, migrating from Zod 3, handling validation errors, generating JSON Schema/OpenAPI, using codecs/transforms, or integrating with React Hook Form, tRPC, Hono, or Next.js. Covers all Zod v4 APIs including top-level string formats, strictObject/looseObject, metadata, registries, branded types, and recursive schemas.

streamdown

Expert guidance for Vercel's Streamdown library - a streaming-optimized react-markdown replacement for AI applications. Use when: (1) Rendering AI-generated markdown from useChat/streamText, (2) Building chat UIs with streaming responses, (3) Migrating from react-markdown to streaming-friendly rendering, (4) Configuring code blocks (Shiki), math (KaTeX), diagrams (Mermaid), (5) Handling incomplete markdown during AI streaming (remend preprocessor), (6) Customizing markdown styling with Tailwind/CSS variables, (7) Securing AI output with rehype-harden (link/image protocols). Triggers: Streamdown, streaming markdown, AI chat markdown, react-markdown replacement, AI Elements Response, incomplete markdown, remend, Shiki themes, Mermaid diagrams, KaTeX math, rehype-harden, isAnimating, markdown streaming.

dmc-py

Expert guidance for building Dash applications with Dash Mantine Components (DMC) v2.x. Use when creating dashboards, forms, data visualization apps with DMC. Covers: MantineProvider theming, style props (m, p, c, bg, w, h), Styles API, callbacks (basic, pattern-matching ALL/MATCH/ALLSMALLER, clientside, background), multi-page apps with Dash Pages, charts (LineChart, BarChart, DonutChart), date pickers, modals, and all 100+ components. Triggers on: dash-mantine-components, DMC, MantineProvider, dmc.Button, dmc.Select, dmc.Modal, dmc.BarChart, Mantine theme, Dash UI components, Dash callbacks, multi-page Dash app, pattern-matching callbacks, clientside callbacks, AppShell.