openrsi (Python)
Toolkit for managing agentic self-improvement pipelines.
Status:
0.0.1placeholder. The API is an early sketch and will change.
Install
pip install openrsi
Usage
import asyncio
from openrsi import Pipeline, StepResult, define_step
pipeline = (
Pipeline(name="demo", max_iterations=3)
.add(define_step("evaluate", lambda ctx: StepResult("evaluate", improved=True)))
.add(define_step("apply", lambda ctx: StepResult("apply", improved=False)))
)
results = asyncio.run(pipeline.run({"goal": "reduce latency"}))
print(results)
Develop
python -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"
pytest
License
MIT
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
openrsi-0.0.1.tar.gz
(2.9 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
File details
Details for the file openrsi-0.0.1.tar.gz.
File metadata
- Download URL: openrsi-0.0.1.tar.gz
- Upload date:
- Size: 2.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8229c27555e8008a1b220bbe2f35baaf2157e3a7571adb30fa3c7aa22555689a
|
|
| MD5 |
a77dd738de61cc1c9aab57a6a68b866a
|
|
| BLAKE2b-256 |
05030054f67545df7cea39015e0c128371a20eaedcafc8546a5c39860c5f52c6
|
File details
Details for the file openrsi-0.0.1-py3-none-any.whl.
File metadata
- Download URL: openrsi-0.0.1-py3-none-any.whl
- Upload date:
- Size: 3.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.11.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4b5d68edef3460af38c96f4753e1be0f8f52a2396e4c2a4efe516e318d1e0170
|
|
| MD5 |
b13e774f3037043a2cf32d483b398f85
|
|
| BLAKE2b-256 |
c55a84395ee24ff5395288be79a281f95a7098a63688836cf997dce805502023
|
