MemoFlow OpenAI adapter for Python
This optional package connects an injected asynchronous OpenAI Responses client to MemoFlow's durable AI invocation, budget, tool-effect, and recorded-replay contracts. It deliberately does not install or pin the OpenAI package.
from memoflow_openai import OpenAIResponsesAdapter, OpenAIResponsesRun
adapter = OpenAIResponsesAdapter(openai_client)
response = await adapter.run(OpenAIResponsesRun(
request={"model": "your-approved-model", "input": "hello"},
budget=estimate,
recorded_replay_key="primary-model-turn",
))
Call the adapter only inside a server-backed MemoFlow activity. Provider exceptions or cancellation after request dispatch are recorded as uncertain outcomes and retain budget liability for reconciliation. Completed replay envelopes are bound to the complete initial Responses request and registered executor names/versions. Reusing a logical key for changed inputs fails before budget admission or provider dispatch.
1 maintainer
Metadata
1 maintainer
Release files for memoflow-openai 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| memoflow_openai-0.1.0.tar.gz | 11.5 kB | With provenance | Details for memoflow_openai-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| memoflow_openai-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for memoflow_openai-0.1.0-py3-none-any.whl |
Total release size: 20.6 kB
Release files / memoflow_openai-0.1.0.tar.gz
| Download URL | memoflow_openai-0.1.0.tar.gz |
|---|---|
| Size | 11.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d0d646242f0140381200efe0e9dd784017367c73530607e0654df2e056c2300d
|
|
BLAKE2b-256 checksum How to use checksums |
473a16acca48d7954a31779284c581e8d280dc11fcdcb2fda43fa4a73fa5c0f2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 16, 2026.
Transparency logRelease files / memoflow_openai-0.1.0-py3-none-any.whl
| Download URL | memoflow_openai-0.1.0-py3-none-any.whl |
|---|---|
| Size | 9.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
517d186431923c251eef89a7c924e74bc0472065966b9f082717e3579b773525
|
|
BLAKE2b-256 checksum How to use checksums |
8e4c95ee1cba5ed1c73ad8624107e6c37b17882fdb0991d699e083b098bf5903
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 16, 2026.
Transparency logSecurity for memoflow-openai 0.1.0
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for memoflow_openai-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 16, 2026.
Transparency logA 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.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
