# cheshire-cat-ai/core

AI agent microservice

Repository: https://github.com/cheshire-cat-ai/core
Canonical: https://ross.abutalabs.com/products/cheshire-cat-ai-core
Homepage: https://cheshirecat.ai
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: ai, chatbot, docker, llm, plugin, assistant, vector-search, agent, framework, function-calling, python, conversational, ag-ui-protocol, mcp, mcp-client
Last push: 2026-07-29T12:44:29+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 92, longevity 93
- inputs: {"age_days": 1302, "days_push": 35, "days_rel": 56, "gap_med": 2.5, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3085, forks 409 (observed 2026-08-28T04:07:42.077967+00:00)

## What it is
Cheshire Cat AI is a Python framework and microservice for building conversational AI agents with LLMs, tools, RAG, and plugins, served with a built-in web UI and REST API. It is designed bottom-up for education and research, letting users learn how AI agents work through a small set of primitives (Agent, Tool, Directive, Hook).

## Use cases
- build a conversational ai chatbot with tools
- learn how ai agents work
- self-host an llm assistant with rag memory
- create a plugin-based ai agent microservice
- add function calling tools to an llm chatbot
- publish an ai agent on the web for research or teaching
- connect an mcp client to a chatbot

## When to choose
- you want a simple, hackable Python framework to learn or teach agent concepts
- you need a self-hosted chatbot microservice with REST API and web UI out of the box
- you want to extend an agent via plugins, tools, and hooks with minimal boilerplate

## When to avoid
- you need a production-stable system - version 2 is an unstable alpha with breaking changes
- you need a lightweight embedded agent library rather than a full microservice
- GPL-3.0 licensing is incompatible with your project

## Facets
- artifact type: framework
- maturity: experimental
- function: agent-framework, chatbot, rag, llm-inference, mcp, web-framework, plugin-system
- domain: artificial-intelligence, large-language-models, chatbots, education, developer-tools
- platform: python, self-hosted, cross-platform
- tags: conversational-ai, function-calling, vector-search, ag-ui-protocol, microservice, learning-framework, gpl-3.0, ai-agents, retrieval-augmented-generation, docker, web-server

## Member repositories
- cheshire-cat-ai/core (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:42.077967+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:27:39.426641+00:00, confidence not recorded.
  - readme: https://github.com/cheshire-cat-ai/core (fetched 2026-08-28T04:07:42.077967+00:00, sha 1d67205cee2c)
  - homepage: https://cheshirecat.ai (fetched 2026-08-29T09:42:55.241588+00:00, sha 7f0658a70ae1)
  - site_page: https://cheshirecat.ai/docs (fetched 2026-08-29T09:42:55.250610+00:00, sha dc2dd35450da)
  - site_page: https://cheshirecat.ai/about (fetched 2026-08-29T09:42:55.252375+00:00, sha 94c2a2312783)
- Data as of 2026-08-30T08:39:29.467469+00:00.