NEVER TRAINED ON · PRIVATE BY DEFAULT · BUILT BY MOZILLA

GITHUB

Integration eve

Return finished web results inside eve.

Cited answers, clean Markdown, matching JSON, and public web tasks for eve, as native, path-derived eve tools.

@tabstack/eve

"which runtimes shipped web search?"

ollama.com/blog

docs.openwebui.com

 

ANSWER

Two runtimes shipped it.

ollama.com/blogdocs.openwebui.com2 cited

First call

Start with a current question.

Search gives your model sources. It still has to build the answer. Tabstack Research completes that answer-building work and returns the cited result through the integration, so the agent receives a finished answer rather than a list of pages to read.

Why eve + Tabstack

eve derives each tool’s name from its filename: add a file under agent/tools/ and the model can call it. @tabstack/eve ships pre-built defineTool definitions you re-export into that directory: schema-enforced output, server-side rendering of JS-heavy pages, and one key for extraction, research, generation, and automation. Tool names stay in lockstep with the @tabstack/langchain, @tabstack/ai, and Python langchain-tabstack packages.

Quickstart

Install the adapter and set your key:

npm install @tabstack/eve eve zod

export TABSTACK_API_KEY="your-key-here"

Re-export a Tabstack tool as the default export of a file named after the tool:

// agent/tools/research_question.ts
export { researchQuestionTool as default } from "@tabstack/eve";
// agent/tools/extract_page_content.ts
export { extractPageContentTool as default } from "@tabstack/eve";

The filename becomes the tool name, and the tools resolve TABSTACK_API_KEY lazily on first call. For a custom key, base URL, or a shared client, build them explicitly:

// agent/tools/research_question.ts
import { createTabstackEveTools } from "@tabstack/eve";

const tools = createTabstackEveTools({ apiKey: process.env.MY_KEY });
export default tools.research_question;

The tools

File name What it does
extract_structured_data.ts Pull specific fields from a URL into a JSON shape you define.
extract_page_content.ts Fetch a page as clean Markdown.
research_question.ts Synthesized answer with cited sources across multiple pages.
generate_structured_data.ts Fetch a page, then AI-transform it into derived or reshaped JSON.
automate_browser_task.ts Run a multi-step, natural-language browser task.

The filename must match the tool name, because eve’s identity is path-derived.

Common use cases

  • Add web research to an eve agent by dropping one file into agent/tools/.
  • Expose only the capabilities a given agent needs, one file each.
  • Share a single configured Tabstack client across every tool.
  • Keep tool names consistent across your TypeScript and Python agents.

Next steps

Note

Good to know.

Automate is public only. The hosted task does not sign in to accounts, in this integration or any other.

Next

Three places to go from here.

START FREE

Install it where you already build.

Start with 10,000 free credits. No credit card required.

pip install tabstack