Skip to main content

CLI interface to use MakoraGenerate as a standalone tool or inside your favourite coding agent.

Project description

Makora CLI

The Makora CLI is a command-line interface (CLI) for interacting with Makora Generate.

Use it as a standalone tool or with your favourite coding agent!

Installation and Setup

Prerequisites

  • Python 3.10+
  • pip

Install

pip install makora

or for editable mode (development), after cloning this repo:

pip install -e .

Verify install

makora --help

Login Before Using Protected Commands

Most commands require authentication first.

  1. Create/copy an API token from: https://generate.makora.com/tokens

  2. Login interactively:

    makora login
    

    or non-interactively:

    makora login --token <token_value_or_file_containing_it>
    
  3. Confirm login state:

    makora info
    

To clear credentials:

makora logout

Subcommands

Below is the summary of available subcommands provided by the package. For a more comprehensive introduction and overview, please see: https://docs.makora.com.

Note: also try consulting each subcommands --help!

Subcommand Login required Purpose
login No Save API credentials for CLI use.
logout No Remove saved credentials.
info No Show version, env vars, and current login status.
generate Yes Validate code and create a new optimization session.
jobs Yes List your sessions/jobs.
stop Yes Stop a running job/session.
kernels Yes List kernels for a session or show kernel code.
check Yes Validate a kernel/problem file without creating a full run.
refcode Yes Show the original reference code for a session.
profile Yes Profile optimized vs reference code on remote hardware.
evaluate Yes Benchmark optimized vs reference code on remote hardware.
expert-generate Yes Generate improved kernel code with additional tools.
document-search Yes Search documents via the additional-tools document search API.
install Yes Install the Makora plugin (currently claude).

Project details


Download files

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

Source Distribution

makora-1.0.3.tar.gz (48.6 kB view details)

Uploaded Source

Built Distribution

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

makora-1.0.3-py3-none-any.whl (78.2 kB view details)

Uploaded Python 3

File details

Details for the file makora-1.0.3.tar.gz.

File metadata

  • Download URL: makora-1.0.3.tar.gz
  • Upload date:
  • Size: 48.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for makora-1.0.3.tar.gz
Algorithm Hash digest
SHA256 00d04a3f587ab51ab00c1c4968930da82b06a1f0a475c6586bf4422603bb4524
MD5 3e839fae0d226375bdcb78f0968394ad
BLAKE2b-256 2f4efca6ad31e0ad6f5fd7ad1d482c1f140e3de7b86d6d61a455de8051cc2cb7

See more details on using hashes here.

File details

Details for the file makora-1.0.3-py3-none-any.whl.

File metadata

  • Download URL: makora-1.0.3-py3-none-any.whl
  • Upload date:
  • Size: 78.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for makora-1.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 9cf671bc87d1739bf70d934f5eb838d6d8c12f3c0e87186486f0874ceeee8cae
MD5 eeadb8b12956cc050251edf9f2c2b038
BLAKE2b-256 cf688b3c5ec0392dbf8791967ecdf26d024c4f1ea346e9cc14f5408cba1fb7b4

See more details on using hashes here.

Supported by

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