Cheshire Cat AI: Build AI agents in plain Python
Cheshire Cat AI is a Python framework for building AI agents from four primitives: agents, tools, directives and hooks.
What is Cheshire Cat AI?
Cheshire Cat AI is a Python framework for building AI agents. You install it with uv, run it, and open a local web interface at localhost:1865, where you pick a model and start chatting with your agent. Everything you build comes from a single import, and the model is built on four primitives: Agent, Tool, Directive and Hook. An agent is a loop that reads the chat, calls tools and answers; a tool is a type-hinted method the model can call; directives act as middleware over the agent loop, covering RAG, memory, skills and guardrails; hooks react to lifecycle events. The project also covers larger setups. You can run multiple agents in one chat, connect Model Context Protocol servers so their tools, prompts and resources are available, and stream tokens, tool calls and lifecycle events over the AG-UI protocol. Models from OpenAI, Anthropic, Gemini, Ollama, OpenRouter and vLLM can be swapped with one line. Plugins are folders that add agents, tools, directives and endpoints, and the API can be extended with a decorator plus built-in role-based auth.
Focus areas: AI Agents.
Who is Cheshire Cat AI for?
- Python developers building custom AI agents
- Learners who want to understand how agents work by coding
- Teams self-hosting multi-agent chat applications
Is Cheshire Cat AI worth it?
A code-first Python framework for developers who want to build and self-host AI agents rather than configure a hosted product
Where Cheshire Cat AI is strong
- Four-primitive model that can be learned quickly
- Model-agnostic, with one-line swapping between providers
- Built-in web UI and plugin folders without boilerplate
Where it falls short
- No pricing information is published on the site
- Requires Python and command-line setup rather than a hosted sign-up
How do you get started with Cheshire Cat AI?
- 01Install with uv and run the ccat command
- 02Open http://localhost:1865 and choose a model
- 03Subclass Agent, add tools or directives, and extend via plugins
Cheshire Cat AI: frequently asked questions
What is Cheshire Cat AI?
It is a Python framework for building AI agents, described on the site as an AI agent framework for learners and creatives.
How do I install it?
The homepage shows installing with uv, adding the cheshire-cat-ai package, and running ccat, which serves a web UI at localhost:1865.
Which models can I use?
The site lists OpenAI, Anthropic, Gemini, Ollama, OpenRouter and vLLM, and says you can swap between them with one line.
How much does it cost?
No pricing is published; the pricing page returns a 404 error, so cost details are not available from the source.
Cheshire Cat AI alternatives
The closest tools in our directory, matched on category, focus areas and audience.
| Tool | Best for | Free plan | Starting price | Focus areas |
|---|---|---|---|---|
| Cheshire Cat AI | Python developers building and self-hosting custom AI agents | Unknown | — | AI Agents |
| Mitra | Buyers exploring AI agents for complex task work | Unknown | — | AI Agents |
| AgentGenesis | Developers assembling AI agents from reusable open-source code | Yes | — | AI Agents |
| GRID 2.0 | Developers adding reliable spreadsheet operations to AI agents | No | — | AI Agents |
| Sublayer | Ruby developers adding AI agents to their products | Unknown | — | AI Agents |
| nventr AI Platform | Enterprises automating agent workflows and document processing | No | $0.99/mo | AI Agents |
| Vivgrid | Teams running agent tools in the cloud with tracing and evaluation | Yes | $25/mo | AI Agents |
| BotDojo | Teams embedding AI agents into existing enterprise workflows | No | — | AI Agents |
| GPTConsole | Developers generating web apps and querying codebases with agents | Yes | — | AI Agents, CLI |
| Godmode | Trying autonomous AI agents through a web interface | Unknown | — | AI Agents |
| Voyager minedojo | Researchers testing LLM agents in open-ended game worlds | Unknown | — | AI Agents |
