agentmods.dev

vstorm-co/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.

About the project

Pydantic Deep Agents is a self-hosted terminal AI assistant and Python framework for building coding, research, and other AI agents. It gives agents tools such as file access, shell commands, planning, memory, sub-agents, sandboxed execution, and MCP connections, and supports different models.

This repository also configures its own agents. See what pydantic-deepagents tells them →

Open on GitHub vstorm-co.github.io
1.1kStars on the repository
17Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Sort RelevanceRecently updatedFewest tokensSecurity gradeRepo starsStars this weekTop rated 16 mods

build-and-compile

01

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Building, compiling, and resolving dependency issues across languages.

not rated 1.1k +10 today A SkillSpector: pass 15 tokens original MIT

code-review

02

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

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

not rated 1.1k +10 today A SkillSpector: pass 16 tokens original MIT

data-formats

03

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

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

not rated 1.1k +10 today A SkillSpector: pass 18 tokens original MIT

git-workflow

05

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

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

not rated 1.1k +10 today A SkillSpector: warn 17 tokens original MIT

performant-code

06

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Writing efficient code that handles large data and tight constraints.

not rated 1.1k +10 today A SkillSpector: pass 14 tokens original MIT

refactor

07

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Refactor code to improve structure and maintainability.

not rated 1.1k +10 today A SkillSpector: pass 12 tokens original MIT

skill-creator

08

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Create new reusable skills from conversation context.

not rated 1.1k +10 today A SkillSpector: pass 11 tokens original MIT

test-writer

10

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Generate comprehensive test suites for existing code.

not rated 1.1k +10 today A SkillSpector: pass 11 tokens original MIT

diagram-design

12

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Best practices for creating research diagrams with Excalidraw MCP tools.

not rated 1.1k +10 today A SkillSpector: pass 16 tokens original MIT

report-writing

13

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Guidelines for writing well-structured, cited research reports.

not rated 1.1k +10 today A SkillSpector: pass 14 tokens original MIT

research-methodology

14

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

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

not rated 1.1k +10 today A SkillSpector: pass 16 tokens original MIT

data-analysis

15

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Comprehensive data analysis skill for CSV files using Python and pandas.

not rated 1.1k +10 today A SkillSpector: pass 15 tokens original MIT

test-generator

16

vstorm-co/pydantic-deepagents

Skill Claude CodeCodex

Generate pytest test cases for Python functions and classes.

not rated 1.1k +10 today A SkillSpector: pass 12 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: