examples

Examples

Agents, patterns, and applications you can build with Deep Agents.

Pattern	Example	Learning Outcome
🚀 Recursive	deep_research	Master the "Thinking Tool" for multi-step web research and strategic reflection.
🏎️ Heterogeneous	nvidia_deep_agent	Orchestrate frontier models with specialized GPU-accelerated research nodes.
🎨 Asset Pipeline	content-builder	Bundle persona memory, task skills, and image generation into a content engine.
📊 Disclosure	text-to-sql	Implement progressive schema exploration for lean, efficient SQL agents.
🔁 Persistent	ralph_mode	Build long-running project loops with fresh context and Git-based memory.
📦 Portable	downloading	Distribute and version "Brain Folders" as portable agent artifacts.
🌐 Distributed	async-subagent	Scale agents across infrastructure using the async Agent Protocol.

Each example has its own README with setup instructions.

Contributing an Example

See the Contributing Guide for general contribution guidelines.

When adding a new example:

• Use uv for dependency management with a pyproject.toml and uv.lock (commit the lock file)
• Pin to deepagents version — use a version range (e.g., >=0.3.5,<0.4.0) in dependencies
• Include a README with clear setup and usage instructions
• Add tests for reusable utilities or non-trivial helper logic
• Keep it focused — each example should demonstrate one use-case or workflow
• Follow the structure of existing examples (see deep_research/ or text-to-sql-agent/ as references)