docs: add pydantic-deep to third-party toolsets

docs/multi-agent-applications.md

@@ -327,3 +327,9 @@ See the [graph](graph.md) documentation on when and how to use graphs.
 The following examples demonstrate how to use dependencies in Pydantic AI:
 
 - [Flight booking](examples/flight-booking.md)
+
+## Community Frameworks
+
+For more advanced multi-agent scenarios with built-in toolsets, consider:
+
+- [Pydantic-Deep](https://github.com/vstorm-co/pydantic-deepagents) — A deep agent framework built on Pydantic AI with ready-to-use toolsets for task planning (`TodoToolset`), filesystem operations (`FilesystemToolset`), and subagent delegation (`SubAgentToolset`). See the [toolsets documentation](toolsets.md#pydantic-deep) for usage examples.

docs/toolsets.md

@@ -708,3 +708,42 @@ toolset = ACIToolset(
 
 agent = Agent('openai:gpt-5', toolsets=[toolset])
 ```
+
+### Pydantic-Deep {#pydantic-deep}
+
+[Pydantic-Deep](https://github.com/vstorm-co/pydantic-deepagents) implements the [Deep Agents](https://blog.langchain.com/deep-agents/) architecture pattern for Pydantic AI. Deep agents are production-grade agents with planning, file system operations, task delegation, and sandboxed code execution — patterns documented from production systems like Claude Code and Manus.
+
+Available toolsets:
+
+- `TodoToolset`: Task planning and progress tracking for agent self-organization
+- `FilesystemToolset`: File operations (ls, read, write, edit, glob, grep, execute)
+- `SubAgentToolset`: Spawn and delegate tasks to specialized subagents
+- `SkillsToolset`: Load and use [agent skills](https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills) from markdown files
+
+The framework also includes multiple backends (in-memory, filesystem, Docker sandbox), automatic conversation summarization, and human-in-the-loop approval workflows.
+
+You will need to install the `pydantic-deep` package.
+
+```python {test="skip" lint="skip"}
+from pydantic_ai import Agent
+from pydantic_deep import create_deep_agent, create_default_deps, DeepAgentDeps
+from pydantic_deep.backends import StateBackend
+from pydantic_deep.toolsets import TodoToolset, FilesystemToolset
+
+# Option 1: Use the pre-configured deep agent
+backend = StateBackend()
+deps = create_default_deps(backend)
+agent = create_deep_agent()
+result = await agent.run("Help me organize my tasks", deps=deps)
+
+# Option 2: Use individual toolsets with your own agent
+backend = StateBackend()
+deps = DeepAgentDeps(backend=backend)
+agent = Agent(
+    'openai:gpt-4.1',
+    toolsets=[TodoToolset(), FilesystemToolset()],
+)
+result = await agent.run("Your prompt", deps=deps)
+```
+
+See the [full demo application](https://github.com/vstorm-co/pydantic-deepagents/tree/main/examples/full_app) for a complete example with a chat interface, file uploads, skills, and streaming responses.