Integration openai-agents
Give OpenAI Agents the web without giving up your privacy.
Cited answers, clean Markdown, matching JSON, and browser tasks for the OpenAI Agents SDK, as native Agents SDK tools.
@tabstack/openai-agents
ollama.com/blog
docs.openwebui.com
ANSWER
Two runtimes shipped it.
Why OpenAI Agents
Tabstack, inside OpenAI Agents.
@tabstack/openai-agents adds Tabstack to the OpenAI Agents SDK as ready-to-use tools. Hand the array to an Agent and it gets cited research, clean page content, matching JSON, and browser tasks.
post /research
query: "which runtimes…"
mode: "balanced"First call
Start with a current question.
OpenAI Agents makes the call, and Tabstack handles the web. Research searches live sources, reads the pages, and returns a cited answer, so your agent gets the findings without running every search itself.
npm install @tabstack/openai-agents @openai/agents zod
export TABSTACK_API_KEY="your-key-here"
import { Agent, run } from "@openai/agents";
import { tabstackTools } from "@tabstack/openai-agents";
const agent = new Agent({
name: "Research assistant",
instructions: "Answer with current information from the web, and always cite sources.",
tools: tabstackTools,
});
const result = await run(agent, "What are Vercel's pricing plans, with sources?");
console.log(result.finalOutput);
Tools
Five tools, one key.
Each Tabstack endpoint is a tool in tabstackTools. Pass the whole array, or import the ones a run should reach.
| Tool | Returns |
|---|---|
research_question | A cited answer from multiple live sources |
extract_page_content | A page as clean Markdown |
extract_structured_data | JSON matching a schema you define |
generate_structured_data | A page transformed into the JSON you describe |
automate_browser_task | A completed browser task, from plain-language steps |