cheshire-cat-ai/core

AI agent microservice

What it solves

It provides a framework for building and understanding AI agents, specifically designed for education and research purposes. It allows users to create and publish agents on the web, making it easier for institutions and companies to share their AI capabilities.

How it works

The framework is designed from the bottom up to be easy to understand and extend through "vibe coding" and agentic engineering. It provides a built-in UI and a REST API playground for interacting with and developing agents.

Who it’s for

It is primarily aimed at researchers, students, and companies who want to learn how AI agents work or publish agents for public access.

Highlights

  • Built for education and research
  • Easy to extend via agentic engineering
  • Includes a built-in user interface and REST API playground
  • Quickstart available via uv

Related

  • Project
    MaestroError/LarAgent

    An AI agent development framework for Laravel that allows developers to create and maintain AI agents using an Eloquent-like API and Laravel-style tooling.

  • Project
    google/adk-web

    A developer UI for the Google Agent Development Kit that simplifies the building, debugging, and orchestration of AI agents.

  • Project
    microsoft/autogen

    AutoGen is a framework for creating multi-agent AI applications that can act autonomously or collaborate with humans using a layered, extensible architecture.

  • Project
    Haohao-end/openagent

    A full-stack AI agent platform for building, orchestrating, and publishing AI applications with visual workflows, RAG integration, and OpenAPI delivery.

  • Project
    scaleapi/scale-agentex

    A framework for building and deploying AI agents that scales from simple chatbots to fully autonomous systems, supporting both synchronous and asynchronous workflows.