Skip to main content

Claire AI

Claire, your assistent with Artificial intelligence in your terminal. (CLI Agent).

It works like a integration of langchain agent in your terminal.

From dev to devs :)

Instalation

You can use Claire on-the-fly without permanently installing it, or install it globally on your system. We recommend using uv or pipx for isolated and safe installations.

Try it without installing (On-the-fly)

If you have uv installed, you can run Claire instantly, just like npx:

uvx claire-ai

Global Installation (Recommended)

Using uv:

uv tool install claire-ai

Using pipx:

pipx install claire-ai

Using standard pip:

pip install claire-ai

Make sure to use a virtual environment if you choose this method.

Once installed, Claire will be available globally in your terminal. You can start using it simply by typing:

claire-ai --help

Commands

1. configure

Command to make authentication, just put your api key (any provider), provider model and the name of the model.

  • Options:
    • --api-key (str): API Key for integrate the LLM model with Claire.
    • --provider-model (str): Provider from the LLM model.
    • --llm-model (str): Name of the model used.

You can see this and more of this command usage just using the --help option.

2. chat

Command to start conversation with Claire, just ask your query and Claire will post your response.

  • Options:
    • --query (str): Query used to ask Claire.

Obs.: Depeding on the provider that you configure, maybe, some dependencies are going to be requested. All from langchain chat models.

You can see this and more of this command usage just using the --help option.

3. install-dependency

Command to install a dependency

  • Options:
    • --dependency-name (str): Name of the dependency that you want to install.

Obs.: If not passing dependency_name, this command will see the provider model that you passed in configuration and will pull the dependency that's needed to Claire works, if it's not installed.

You can see this and more of this command usage just using the --help option.

4. uninstall-dependency

Command to uninstall a dependency

  • Arguments:
    • dependency_name (str): Name of the dependency that you want to uninstall.

You can see this and more of this command usage just using the --help option.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

claire_ai-0.1.2.tar.gz (4.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

claire_ai-0.1.2-py3-none-any.whl (8.0 kB view details)

Uploaded Python 3

File details

Details for the file claire_ai-0.1.2.tar.gz.

File metadata

  • Download URL: claire_ai-0.1.2.tar.gz
  • Upload date:
  • Size: 4.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for claire_ai-0.1.2.tar.gz
Algorithm Hash digest
SHA256 0cc94f7d52112953f097d64c761df4f648c8d722cb10bbbec950d7d7267e7efb
MD5 c569fe0638a7b99ad9d40c1be64bda5a
BLAKE2b-256 77864eeadbe48374c5ba50091ee882cb064079d8fcd2c748939d2fdec6249130

See more details on using hashes here.

File details

Details for the file claire_ai-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: claire_ai-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 8.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.3 {"installer":{"name":"uv","version":"0.11.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for claire_ai-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 66666872c03dee69cafbcfb99c7d6ae5a72d928f674686d35d20eaaa9d795827
MD5 5d21de0964cc8e702e1833c51a16f179
BLAKE2b-256 a780523e1e25c80d83955cc851dc1332767bd49a386cabf75fa7b90b782ee359

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 files

0.1.0

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page