agent-sense
Human-agent interaction SDK with accessibility and dialogue management
Part of the AumOS open-source agent infrastructure portfolio.
Features
- User context detection infers expertise level, situation, and channel (web, mobile, voice) from conversation signals, enabling responses calibrated to the user's knowledge and environment
- Confidence annotation and calibration — the
ConfidenceAnnotatorattaches per-claim confidence signals to agent responses and theDisclaimermodule adds appropriate hedging when confidence falls below configurable thresholds - Human handoff orchestration:
HandoffRouterevaluates confidence and topic signals, packages the conversation context, and routes to the appropriate human queue with full conversation history attached - WCAG 2.1 AA accessibility checker inspects HTML fragments for color contrast, missing image alternatives, heading hierarchy violations, and ambiguous link text
- AI disclosure and transparency utilities that inject required disclosure notices and explain the agent's limitations for regulated interaction contexts
- Suggestion engine ranks follow-up prompts and clarifying questions by relevance to the current conversation turn
- Channel adapters for web, mobile, and voice normalize input and format output appropriately for each surface
Quick Start
Install from PyPI:
pip install agent-sense
Verify the installation:
agent-sense version
Basic usage:
import agent_sense
# See examples/01_quickstart.py for a working example
Documentation
Enterprise Upgrade
For production deployments requiring SLA-backed support and advanced integrations, contact the maintainers or see the commercial extensions documentation.
Contributing
Contributions are welcome. Please read CONTRIBUTING.md before opening a pull request.
License
Apache 2.0 — see LICENSE for full terms.
Part of AumOS — open-source agent infrastructure.
Metadata
Release files for agent-sense 0.2.0
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 | |
|---|---|---|---|---|
| agent_sense-0.2.0.tar.gz | 126.2 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| agent_sense-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 240.9 kB
Release files / agent_sense-0.2.0.tar.gz
| Download URL | agent_sense-0.2.0.tar.gz |
|---|---|
| Size | 126.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
fb847c7b74b369c86142c22ffdaf69d80dfff8cc4192374346578a545a41eedc
|
|
BLAKE2b-256 checksum How to use checksums |
bb8a14d8ad3400f45d5c9604538758856e47532bcb40a41e62475588f3e79c73
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / agent_sense-0.2.0-py3-none-any.whl
| Download URL | agent_sense-0.2.0-py3-none-any.whl |
|---|---|
| Size | 114.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1fdc2a4847bc822b6e4be7022c52cdd89e21dd4a976c9003fd4dfe635eddb921
|
|
BLAKE2b-256 checksum How to use checksums |
95b471b4972fb8e5c025c443dad373f6ebac12d02b174abef9153ebbd4704787
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Security for agent-sense 0.2.0
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A 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.