honornet-agent-presentation-openai-agents
Tools for the OpenAI Agents SDK that make an OpenAI-Agents agent HonorNet-capable — able to present an issuer-signed credential, an owner-signed mandate, and a per-transaction proof to a HonorNet acceptance endpoint, and receive an approve/decline verdict.
It is a shim, not a framework
This wrapper is a protocol shim under HonorNet's hard rule 3, the same boundary as the MCP client it wraps. The analog is Visa publishing an EMV kernel: the kernel holds the card's key, mints the per-transaction cryptogram, and presents it — it decides nothing about what the cardholder buys.
These tools do exactly that and no more:
- hold an issuer-signed credential (
load_credential), - hold an owner-signed mandate (
load_mandate), - mint the per-transaction proof of possession, assemble the three-part
ADR-009 bundle, and present it (
present).
They decide nothing about what the agent buys, ranks, or chooses, and never
call a model. The approve/decline verdict is always the network's; present
relays it verbatim and adds no judgment. The tool set is exactly the three the
core client defines — this wrapper cannot add a fourth.
Install
pip install honornet-agent-presentation-openai-agents
This pulls the core honornet-agent-presentation client (which carries the
pure-Python signing, zero third-party deps) and openai-agents.
Use
from agents import Agent
from honornet_presentation import PresentationClient
from honornet_presentation_openai_agents import make_honornet_tools
client = PresentationClient(
agent_seed=AGENT_SEED, # the agent's own Ed25519 seed
endpoint="https://api.honornet.ai/authorize",
api_key=SANDBOX_OR_LIVE_CALLER_KEY, # operator-configured, not an agent argument
)
agent = Agent(
name="checkout-agent",
tools=make_honornet_tools(client), # -> [load_credential, load_mandate, present]
)
The agent decides what the transaction is; the operator configures where it
is presented (the endpoint); the shim decides neither. See
epic-AC-530
and the four-party model.
License
Apache-2.0.
Metadata
Release files for honornet-agent-presentation-openai-agents 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 | |
|---|---|---|---|
| honornet_agent_presentation_openai_agents-0.1.0.tar.gz | 8.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| honornet_agent_presentation_openai_agents-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 17.3 kB
Release files / honornet_agent_presentation_openai_agents-0.1.0.tar.gz
| Download URL | honornet_agent_presentation_openai_agents-0.1.0.tar.gz |
|---|---|
| Size | 8.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d0e1afe51da7830608594824cb717ef680e1c97558d6cc6f141d4f72d3b40c75
|
|
BLAKE2b-256 checksum How to use checksums |
60218f931e2cd0dbbd5339987440c2da597174ab24996ab3b2aefdd6d9624061
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 12, 2026.
Transparency logRelease files / honornet_agent_presentation_openai_agents-0.1.0-py3-none-any.whl
| Download URL | honornet_agent_presentation_openai_agents-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8b312349ca6599bd5323e29957c3c71f5543acb4572c519c14c734a20beb7a44
|
|
BLAKE2b-256 checksum How to use checksums |
b7edab94ae915afe442aace535e320073b1463799ccf99742e2121973ae24ad9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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 12, 2026.
Transparency log