Atomic Agents

Marketplace Verified Active

Official plugins for the Atomic Agents framework - a lightweight, modular system for building AI agents with Pydantic and Instructor

1 Plugin

Purpose

To provide a lightweight, modular, and maintainable framework for building predictable and reliable AI agents using Python, Pydantic, and Instructor.

Features

Lightweight and modular agent framework
Built with Pydantic and Instructor for predictable outputs
Supports custom context providers for dynamic information
Enables chaining of agents and tools
Includes a CLI for managing tools and components

Use Cases

Building custom AI assistants with structured inputs and outputs
Developing multi-agent systems with clear component separation
Integrating LLMs into Python applications with strong typing
Creating reusable AI components for diverse applications

Non-Goals

Replacing existing LLM providers (e.g., OpenAI, Groq); it integrates with them
Providing a low-level interface to LLMs; it abstracts this complexity
Being a full-fledged application builder out-of-the-box; it's a framework for building applications

Documentation

info:Configuration & parameter referenceWhile the README details concepts and usage, specific configuration parameters and their defaults for the framework itself are not explicitly listed.

Code Execution

info:ValidationThe framework relies on Pydantic for schema validation, which is good, but the extent of sanitization within the framework itself isn't fully detailed.

Installation

/plugin marketplace add BrainBlend-AI/atomic-agents

Contains 1 extensions

Plugin (1)

Atomic Agents Plugin

Skills plus explorer and reviewer subagents for building, scaffolding, understanding, and auditing applications with the Atomic Agents Python framework. Includes the umbrella `framework` skill, action-oriented `create-atomic-schema` / `create-atomic-agent` / `create-atomic-tool` / `create-atomic-context-provider` skills, the `new-app` scaffolder, progressive-disclosure reference material for prompts, orchestration, memory, hooks, providers, project structure, and testing, and isolated-context subagents for codebase mapping and code review.

Quality Score

Verified

95 /100

Analyzed 1 day ago

Trust Signals

Last commit15 days ago

GitHub owner BrainBlend-AI

Stars5.9k

LicenseMIT

Status

View Source

Similar Extensions

Stripe

100

One-stop shop for building AI-powered products and businesses with Stripe.

Marketplace

stripe

Context Mode

100

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 15 platforms

Marketplace

mksglu

Claude Code Plugins

Production-ready workflow orchestration with 80 focused plugins, 185 specialized agents, and 153 skills - optimized for granular installation and minimal token usage

Marketplace

wshobson

Compound Engineering

Cursor plugin marketplace for Every Inc plugins

Marketplace

EveryInc