Kitaru OpenAI Agents adapter
Record OpenAI Agents SDK runs with Kitaru. The adapter is non-streaming: it preserves the native RunResult while recording each run as a Kitaru session with root and observed activity nodes.
Install
uv add kitaru-openai-agents
Use
import uuid
from agents import Agent
from kitaru_openai_agents import KitaruRunner
agent = Agent(
name="assistant",
instructions="Answer in one concise sentence.",
model="gpt-5-nano",
)
runner = KitaruRunner(
agent_id=uuid.UUID("018f0000-0000-7000-8000-000000000100"),
session_name="openai-agents-example",
)
result = runner.run_sync(agent, "Hello")
print(result.final_output)
KitaruRunner.run() and KitaruRunner.run_sync() accept the same run arguments as the OpenAI Agents SDK Runner. Kitaru workers provide task, replay, and authentication context through the standard task environment.
The adapter supports bounded replay of non-streaming runs. See the OpenAI Agents SDK adapter guide for supported overrides and tool policies, capture limits, approval and resume boundaries, and recording-failure behavior.
Links
Licensed under Apache-2.0.
1 maintainer
Metadata
1 maintainer
Release files for kitaru-openai-agents 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 | |
|---|---|---|---|
| kitaru_openai_agents-0.2.0.tar.gz | 17.3 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| kitaru_openai_agents-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 35.7 kB
Release files / kitaru_openai_agents-0.2.0.tar.gz
| Download URL | kitaru_openai_agents-0.2.0.tar.gz |
|---|---|
| Size | 17.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c2651f1ce6bce5a34eacf1f22eaca8469d9e779937ab7c17073f27b5e68ff3ba
|
|
BLAKE2b-256 checksum How to use checksums |
b18359696d90b1b553f7164f55a13c2fab4b84317884ce7d960986d86e7964ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Sep 1, 2026.
Transparency logRelease files / kitaru_openai_agents-0.2.0-py3-none-any.whl
| Download URL | kitaru_openai_agents-0.2.0-py3-none-any.whl |
|---|---|
| Size | 18.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d68fbdbce6b9d342e370967863b43f8d55a9c7a2d8d373c9458cf86c15858abc
|
|
BLAKE2b-256 checksum How to use checksums |
68600219d23f70a0b0ad39a6172dbcf1e49fc690e9506b61285897fa216e4b23
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Sep 1, 2026.
Transparency log
