## What - **template-browsing-agent**: add the `## Demo` section (in the standard position, right after "Why we built this") pointing at the existing Cloudinary demo video. The video was already registered for this template on the website but the README had no Demo section, so it never appeared for people cloning the template. - **template-chat-with-pdf** and **template-deep-search**: remove the top-of-README intro image (``) and delete the `assets/header.png` files. These two were the only templates carrying a header image, which is inconsistent with every other template and added multi-MB binaries to the repo. ## Why Template Demo sections are the convention across the templates directory; browsing-agent was the sole template with a registered video but no section to show it. The two header images were one-off inconsistencies and heavy binaries. ## Test plan - Confirmed browsing-agent's embedded video URL matches the registered `videoUrl`. - Verified the two READMEs now start cleanly with their `# Title` heading and the `assets/` directories are gone. - No package/code changes — template README + asset content only, so no changeset required. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## ELI5 This PR adds a demo video to one template and removes header images from two others. It makes the template documentation more consistent without changing application code. ## Changes - Added a `## Demo` section to `template-browsing-agent/README.md`. - Linked the Cloudinary-hosted demo video. - Removed header image references and related `assets/header.png` files from: - `template-chat-with-pdf` - `template-deep-search` - No package or code changes are included. - No changeset is required. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: mastracode <284800079+mastra-platform[bot]@users.noreply.github.com> |
History
|
|
|---|---|---|
| .. | ||
| src/mastra | ||
| .env.example | ||
| .gitignore | ||
| CONTRIBUTING.md | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
Deep Search
An AI research assistant that evaluates its own work. It searches, checks if the results actually answer your question, identifies what's missing, and keeps going until it gets there. Uses Exa for web search and page scraping. Inspired by OpenAI's deep research and Perplexity. Built with Mastra.
Why we built this
This template shows how Mastra's workflow primitives and agent orchestration come together: nested workflows, suspend/resume for human input, and multiple specialized agents coordinating on a single task.
Demo
This demo runs in Mastra Studio, but you can connect this workflow to your React, Next.js, or Vue app using the Mastra Client SDK or agentic UI libraries like AI SDK UI, CopilotKit, or Assistant UI.
Features
- Self-evaluating research loops that identify gaps and keep searching
- Human-in-the-loop with suspend/resume for clarifying questions
- Multiple specialized agents coordinating on a single task
- Web search and page scraping via Exa
- Sourced answers with citations
Prerequisites
- OpenAI API key — used by default, but you can swap in any model
- Exa API key — for web search and page scraping
Quickstart 🚀
- Clone the template
- Run
npx create-mastra@latest --template deep-searchto scaffold the project locally.
- Run
- Add your API keys
- Copy
.env.exampleto.envand fill in your keys.
- Copy
- Start the dev server
- Run
npm run devand open localhost:4111 to try it out.
- Run
Making it yours
Open Studio and trigger the deep-search workflow with your research question. The workflow asks a few clarifying questions — answer them and resume. Watch the console as it searches, evaluates, and iterates until you get a sourced answer.
Swap in a different search provider, add your own evaluation criteria, or wire the workflow into your app using the Mastra Client SDK. The agents and workflow steps are all in src/ — edit them directly to fit your use case.
About Mastra templates
Mastra templates are ready-to-use projects that show off what you can build — clone one, poke around, and make it yours. They live in the Mastra monorepo and are automatically synced to standalone repositories for easier cloning.
Want to contribute? See CONTRIBUTING.md.