atomic-agents

Atomic Agents is a Python framework that brings software engineering principles to AI agent development. Key features: - Focus on practical business applications rather than fancy autonomous clickbait demos - Modular design inspired by Atomic Design, breaking AI systems into reusable components - Structured input/output using Pydantic schemas for predictable behavior - Separation of concerns (prompts, tools, memory) for fine-grained control - Easy chaining of agents and tools to build complex workflows It enables building AI systems that are modular, controllable and aligned with real-world requirements. Think of it as "LEGO blocks for AI agents".

For those who don't know yet, Atomic Agents ( https://github.com/KennyVaneetvelde/atomic_agents ) is designed to be modular, extensible, and easy to use. Components in the Atomic Agents Framework should always be as small and single-purpose as possible, similar to design system components in Atomic Design. Even though Atomic Design cannot be directly applied to AI agent architecture, a lot of ideas were taken from it. The resulting framework provides a set of tools and agents that can be combined to create powerful applications. The framework is built on top of Instructor and uses Pydantic for data validation and serialization. For those who have been following it for a bit, it just got a lot easier to build new agents using any client supported by Instructor, including local agents. I highly recommend checking out: - The basic custom cha