Agents & tools

Configure a provider

Providers are ordinary actor dependencies. OpenAI, Anthropic, and Google ship with typed model catalogs and read TW_OPEN_AI_KEY, TW_ANTHROPIC_KEY, and TW_GOOGLE_AI_KEY. Use Provider for custom OpenAI-compatible hosts.

import { Actor, Anthropic } from "taskwish";

export const { actor } = Actor("Researcher")
  .use(Anthropic);

Agent steps

Agents can reason and call declared tools while deterministic steps prepare inputs, validate results, and produce side effects. Their streamed lifecycle is visible in Console.

import { Agent, Step } from "taskwish";
import { actor } from "./researcher";

export const { research } = actor()
  .on("Command", "research")

  .input({ question: "string" })

  .run(
    Agent({
      model: "anthropic/claude-sonnet-4-6",
      instructions: "Answer with concise, cited findings.",
    }),

    Step("answerQuestion", function () {
      return this.agent.generate({ prompt: this.input.question });
    }),
  )

  .meta({
    description: "Research a question with Claude",
  });

Start from a working architecture

The agent-loops template includes 18 patterns such as ReAct, reflection, evaluator-optimizer, supervisor-worker, and human approval. The agent-graphs template includes six topologies for routing, parallel work, map-reduce, hierarchy, and fallback.

bunx @taskwish/create-project my-agents --template agent-loops