motive
Answer why did the agent do that? with empirically-grounded explanations for AI agent decisions.
motive uses hierarchical occlusion saliency: mask segments of the input context, measure how much each one affects the model's decision, and surface ranked importance scores and counterfactual what-ifs. No model self-reports. No local weights required. Works with any OpenAI-compatible endpoint.
Installation
pip install motive
Quickstart
from openai import AsyncOpenAI
from motive import SaliencyEngine, Segment
engine = SaliencyEngine(
client=AsyncOpenAI(base_url="...", api_key="..."),
model="your-model",
)
result = engine.explain(messages=messages, segments=segments, tools=tools)
print(result.summary())
See examples/demo_saliency.py for a full working example.
1 maintainer
Metadata
1 maintainer
Release files for motive 0.0.2
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 | |
|---|---|---|---|---|
| motive-0.0.2.tar.gz | 82.8 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| motive-0.0.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 96.1 kB
Release files / motive-0.0.2.tar.gz
| Download URL | motive-0.0.2.tar.gz |
|---|---|
| Size | 82.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6cdc9dfbc524199d0818cebd7d6c324a06f40b31200c808a5e926eb2bfe1dc3f
|
|
BLAKE2b-256 checksum How to use checksums |
5d04bb2b51e6ec1d84058d4ec545146f458253eaab93ddadde4c014277b4e62a
|
| 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 Jun 5, 2026.
Transparency logRelease files / motive-0.0.2-py3-none-any.whl
| Download URL | motive-0.0.2-py3-none-any.whl |
|---|---|
| Size | 13.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
554764657ec34d2aee7a1907949ef1d8e1fdc3532e46a5181bb36989d06770a5
|
|
BLAKE2b-256 checksum How to use checksums |
72a420c4b332bcac95380b8473d13149ef7d7dcb1af560145d5f1095471f50de
|
| 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 Jun 5, 2026.
Transparency logSecurity for motive 0.0.2
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
All 2 files in this release have been uploaded with provenance metadata.
Attestation for motive-0.0.2.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 Jun 5, 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.
