clai

(pronounced "clay")

Command line interface to chat to LLMs, part of the Pydantic AI project.

Usage

You'll need to set an environment variable depending on the provider you intend to use.

E.g. if you're using OpenAI, set the OPENAI_API_KEY environment variable:

export OPENAI_API_KEY='your-api-key-here'

Then with uvx, run:

uvx clai

Or to install clai globally with uv, run:

uv tool install clai
...
clai

Or with pip, run:

pip install clai
...
clai

Either way, running clai will start an interactive session where you can chat with the AI model. Special commands available in interactive mode:

/exit: Exit the session
/markdown: Show the last response in markdown format
/multiline: Toggle multiline input mode (use Ctrl+D to submit)
/cp: Copy the last response to clipboard

Help

usage: clai [-h] [-l] [--version] [-m MODEL] [-a AGENT] [-t CODE_THEME] [--no-stream] [--mcp-config MCP_CONFIG] [prompt]

Pydantic AI CLI v...

subcommands:
  web           Start a web-based chat interface for an agent
                Run "clai web --help" for more information

positional arguments:
  prompt                AI prompt for one-shot mode. If omitted, starts interactive mode.

options:
  -h, --help            show this help message and exit
  -l, --list-models     List all available models and exit
  --version             Show version and exit
  -m MODEL, --model MODEL
                        Model to use, in format "<provider>:<model>" e.g. "openai:gpt-5" or "anthropic:claude-sonnet-4-6". Defaults to "openai:gpt-5".
  -a AGENT, --agent AGENT
                        Custom Agent to use: a module path like "module:variable" or a YAML/JSON spec file like "agent.yml"
  -t CODE_THEME, --code-theme CODE_THEME
                        Which colors to use for code, can be "dark", "light" or any theme from pygments.org/styles/. Defaults to "dark" which works well on dark terminals.
  --no-stream           Disable streaming from the model
  --mcp-config MCP_CONFIG
                        Path to MCP servers configuration file (JSON, using the same mcpServers shape as Claude Desktop, Claude Code, and Cursor).

For more information on how to use it, see the CLI documentation.

Web Chat UI

Launch a web-based chat interface:

clai web -m openai:gpt-5.2

Web Chat UI

This will start a web server (default: http://127.0.0.1:7932) with a chat interface.

You can also serve an existing agent. For example, if you have an agent defined in my_agent.py:

from pydantic_ai import Agent

my_agent = Agent('openai:gpt-5.2', instructions='You are a helpful assistant.')

Launch the web UI with:

clai web --agent my_agent:my_agent

For full Web UI documentation, see Web Chat UI.

Release files for clai 2.46.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for clai 2.46.0
File	Size	Uploaded
clai-2.46.0.tar.gz	4.8 kB	Sep 19, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for clai 2.46.0
File	Interpreter	ABI	Platform	Reset
clai-2.46.0-py3-none-any.whl 4.4 kB Sep 19, 2026	Python 3	none	any	Details

Total release size: 9.3 kB

Release files / clai-2.46.0.tar.gz

Download URL	clai-2.46.0.tar.gz
Size	4.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`e514ab9881fc1bdadb90cfa3f9c5424e55748c04449abc80506b4fd462734b27`
BLAKE2b-256 checksum How to use checksums	`e83c2da8c81033aa51e08ad9dadfc2b6184d60b584faa6d2904f7c085d389c60`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.13`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/pydantic/pydantic-ai
Publishing commit: github.com/pydantic/pydantic-ai/tree/c4898abb54dc25ae6f6aef208a4c0661b30a455e

Workflow

Publishing configuration: github.com/pydantic/pydantic-ai/blob/c4898abb54dc25ae6f6aef208a4c0661b30a455e/.github/workflows/ci.yml
Publishing logs: github.com/pydantic/pydantic-ai/actions/runs/35419741586/attempts/1

Artifact

Subject: clai-2.46.0.tar.gz
SHA-256 checksum: e514ab9881fc1bdadb90cfa3f9c5424e55748c04449abc80506b4fd462734b27 Verifying attestations

Release files / clai-2.46.0-py3-none-any.whl

Download URL	clai-2.46.0-py3-none-any.whl
Size	4.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`f1e568a59c2ff5c6b4c9d993edf575012d76fb7a58f80b76c5dd784fb04ff862`
BLAKE2b-256 checksum How to use checksums	`4845709d9fa07ddb809c816313c0dd214cb2f8a5a71cd4735a5465bd6e451571`
Upload date	Sep 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.13.13`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/pydantic/pydantic-ai
Publishing commit: github.com/pydantic/pydantic-ai/tree/c4898abb54dc25ae6f6aef208a4c0661b30a455e

Workflow

Publishing configuration: github.com/pydantic/pydantic-ai/blob/c4898abb54dc25ae6f6aef208a4c0661b30a455e/.github/workflows/ci.yml
Publishing logs: github.com/pydantic/pydantic-ai/actions/runs/35419741586/attempts/1

Artifact

Subject: clai-2.46.0-py3-none-any.whl
SHA-256 checksum: f1e568a59c2ff5c6b4c9d993edf575012d76fb7a58f80b76c5dd784fb04ff862 Verifying attestations