Skip to main content

Coding-Machine

A Machine that produces code.

In order to launch it from the command line or as a Python subprocess:

echo "Theodotos-Alexandreus: Produce the code that does that, machine." \
  | uvx coding-machine \
    --provider-api-key=sk-proj-... \
    --github-token=ghp_... 

Or, with a local pip installation:

pip install coding-machine

Set the environment variables:

export PROVIDER_API_KEY="sk-proj-..."
export GITHUB_TOKEN="ghp_..."

Then:

coding-machine multilogue.txt

Or:

coding-machine multilogue.txt new_turn.txt

Or:

cat multilogue.txt | coding-machine

Or:

cat multilogue.txt | coding-machine > tmp && mv tmp multilogue.txt

Or:

(cat multilogue.txt; echo:"Theodotos: What do you think, Coding-Machine?") \
  | coding-machine

Or:

cat multilogue.txt new_turn.txt | coding-machine

Or:

cat multilogue.txt new_turn.txt | coding-machine >  tmp && mv tmp multilogue.txt

Or, if you have installed other machines:

cat multilogue.md | coding-machine \
  | summarizing-machine | judging-machine > summary_judgment.md

Or use it in your Python code:

# Python
import coding_machine

Metadata

Release files for coding-machine 0.0.1

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

Source distribution (sdist)

Source distribution for coding-machine 0.0.1
File Size Uploaded Provenance
coding_machine-0.0.1.tar.gz 15.9 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for coding-machine 0.0.1
File Interpreter ABI Platform
coding_machine-0.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 37.8 kB

Release files / coding_machine-0.0.1.tar.gz

Download URL coding_machine-0.0.1.tar.gz
Size 15.9 kB
Tags Source
SHA-256 checksum
How to use checksums
65c3ce587fed61e402f6f91f182cc2eb106caaa81724c7f4fcbd9be411ee4412
BLAKE2b-256 checksum
How to use checksums
dabc114902fc5e3b6c2b643e05e225aa58ee92468ee34ee80773b88899a6a7bc
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.25

Release files / coding_machine-0.0.1-py3-none-any.whl

Download URL coding_machine-0.0.1-py3-none-any.whl
Size 22.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9d12aba9265e28ed35f696e08fd644c7bb7b785d82edd35b235820339e4b9d62
BLAKE2b-256 checksum
How to use checksums
eb47503d245cb154b2e896eb9d86e6c0b5919157070602f4907a6f381ccad58e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.9.25

Security for coding-machine 0.0.1

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page