Skip to main content
ClaudeWave
EN, English
vstorm-co / Subagents

pydantic-deepagents

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

  • 1.1k stars
  • 140 forks
  • 3 open issues
  • Language: Python
  • License: MIT
  • updated
Install in ClaudeView on GitHub

Install

Terminal
git clone https://github.com/vstorm-co/pydantic-deepagents && cp pydantic-deepagents/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.
Installable items

16 items in this repository

build-and-compileSkill

Building, compiling, and resolving dependency issues across languages

Install
code-reviewSkill

Systematic code review for bugs, security, style, and performance

Install
data-analysisSkill

Comprehensive data analysis skill for CSV files using Python and pandas

Install
data-formatsSkill

Working with diverse data formats: binary, text, structured, and custom

Install
diagram-designSkill

Best practices for creating research diagrams with Excalidraw MCP tools

Install
environment-discoverySkill

Systematic exploration of unknown environments before starting work

Install
git-workflowSkill

Git operations: commits, branches, PRs, and conflict resolution

Install
performant-codeSkill

Writing efficient code that handles large data and tight constraints

Install
refactorSkill

Refactor code to improve structure and maintainability

Install
report-writingSkill

Guidelines for writing well-structured, cited research reports

Install
research-methodologySkill

Best practices for systematic research, source evaluation, and evidence gathering

Install
skill-creatorSkill

Create new reusable skills from conversation context

Install
systematic-debuggingSkill

Systematic approach to diagnosing and fixing errors

Install
test-generatorSkill

Generate pytest test cases for Python functions and classes

Install
test-writerSkill

Generate comprehensive test suites for existing code

Install
verification-strategySkill

Thorough verification of completed work before declaring done

Install
README

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
Use cases
Dev Tools Research Automation
Topics
agent-frameworkai-agentsanthropicclaude-codeclicoding-agentdeep-researchdocker-sandboxllmsmcpplaywrightpydanticpydantic-aipythonsubagentstuivstorm
Frequently asked

What people ask about pydantic-deepagents

What is vstorm-co/pydantic-deepagents?

vstorm-co/pydantic-deepagents is subagents for the Claude AI ecosystem. Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model. It has 1.1k GitHub stars and its last recorded update is dated 2026-10-20.

How do I install pydantic-deepagents?

You can install pydantic-deepagents by cloning the repository (https://github.com/vstorm-co/pydantic-deepagents) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is vstorm-co/pydantic-deepagents safe to use?

Our security agent has analyzed vstorm-co/pydantic-deepagents and assigned a Trust Score of 97/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.

Who maintains vstorm-co/pydantic-deepagents?

vstorm-co/pydantic-deepagents is maintained by vstorm-co. The last recorded GitHub activity is dated 2026-10-20, with 3 open issues.

Are there alternatives to pydantic-deepagents?

Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.

Project homepage
https://vstorm-co.github.io/pydantic-deepagents/