auto research harness based on opencode server
Project description
ARH
ARH is a small CLI for autoresearch-style deep learning iteration.
Install
From PyPI:
uv tool install arh-oc
Then run the CLI as:
arh --help
From this repo:
uv pip install -e .
Or inside another research repo:
pip install -e /path/to/arh
Basic flow
Inside your training repo:
arh contract
arh setup
arh research
arh feedback
For continuous looping:
arh research-loop
What each command does
arh contract: creates or updatesresearch.mdarh setup: inspects the train entrypoint, patches smoke markers, and runs setup smokearh research: creates the next experiment, commits it, and launches it intmuxarh feedback: reads the latest finished run and appends feedback toresults.mdarh research-loop: alternatesfeedbackandresearchuntil stopped or a stop condition is reached
Files created in your research repo
research.md: research contractresults.md: experiment and feedback log.autoresearch/logs/: smoke and experiment logs
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
arh_oc-0.1.0.tar.gz
(23.8 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
arh_oc-0.1.0-py3-none-any.whl
(35.8 kB
view details)
File details
Details for the file arh_oc-0.1.0.tar.gz.
File metadata
- Download URL: arh_oc-0.1.0.tar.gz
- Upload date:
- Size: 23.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.24 {"installer":{"name":"uv","version":"0.9.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e40ae5595baeb1b6dbae02e76cc5ba966cf33359a890e90d231d35a356a16b30
|
|
| MD5 |
ced4bc65f46d636adfff220dd8763891
|
|
| BLAKE2b-256 |
ed464e8b431c55ae1d7fa25ac92d70d99127017ce9f2bccd579f4eb26fae4e93
|
File details
Details for the file arh_oc-0.1.0-py3-none-any.whl.
File metadata
- Download URL: arh_oc-0.1.0-py3-none-any.whl
- Upload date:
- Size: 35.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.24 {"installer":{"name":"uv","version":"0.9.24","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
79aa37dfe72e6c1219b0846154ecb039057bf222ad6b5a18c00d893335c26332
|
|
| MD5 |
b638f2ec1eeb245877e6e40f771500c1
|
|
| BLAKE2b-256 |
247d65f67322704a316924bae835cc14ab4327a2ed8ecafaf05defeaa5c683ac
|