autoresearchstudio
Generalized autonomous ML research framework. Inspired by Karpathy's autoresearch.
Install
pip install autoresearchstudio
Quick start
# Initialize a project (use --from-template karpathy for LLM pretraining)
ars init
# Edit autoresearch.yaml to match your project
# Start a run
ars setup --tag mar21
# The AI agent then uses these commands in a loop:
ars run --description "baseline"
ars log --description "baseline"
ars judge
1 maintainer
Metadata
1 maintainer
Release files for autoresearchstudio 0.4.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| autoresearchstudio-0.4.5.tar.gz | 18.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| autoresearchstudio-0.4.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 41.3 kB
Release files / autoresearchstudio-0.4.5.tar.gz
| Download URL | autoresearchstudio-0.4.5.tar.gz |
|---|---|
| Size | 18.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3f348800e10be36c86a0ce988e03fd91dc04fef332f8ab7e70625be34a288407
|
|
BLAKE2b-256 checksum How to use checksums |
78b45f9823462bdea4a947b7bb5c1c35f8eb8aa7949c0b5decb232af6e2ecbd9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
Release files / autoresearchstudio-0.4.5-py3-none-any.whl
| Download URL | autoresearchstudio-0.4.5-py3-none-any.whl |
|---|---|
| Size | 22.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
dd834a9715c060df9688e802eea3691c5a8d62c6de81dc2d5ae76b33d74f3c0d
|
|
BLAKE2b-256 checksum How to use checksums |
c694e73b68104dffd3a54dff7f28c4dc9bdba66b7c1643d5077741b4591f92bd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.5
|
