Skip to main content

KUMA geometric wordmark banner

KUMA

KUMA Python SDK
Knowledge-grounded Universal Measurement for Agents

English  |  简体中文

KUMA is the public Python SDK for testing Agent behavior through a strict Run protocol and bounded Evidence capture. Official services are reached only through public HTTPS; the SDK does not run Agents, execute models, or expose private evaluation logic.

Core capabilities

  • Synchronous, framework-neutral Case and Judge workflow.
  • Official or custom Providers, including fully local runs.
  • Bounded file, log, and optional trace Evidence.
  • upload_diff=True with track_files=True sends safe patches; default is hash-only. Trace attaches to configured OTel and uploads only recorded tool content, never invented arguments/results. Setup and source upgrade.
  • Default Trace budget: 8 MiB per Run. Agent output: 4 MiB canonical JSON; Runtime Evidence: 5 MiB; complete multipart upload: 8 MiB. Stricter server limits still apply; output is rejected rather than truncated.
  • Strategy Groups choose the testing method; an Agent Profile supplies only the Agent, scenario, expected-behavior, and prohibited-boundary context.

Install

Install from PyPI. Requires Python 3.10 or newer; Git is not required:

python -m pip install --upgrade kuma-defuzex

Run this in the Python environment used by your Agent, then restart the Agent. The package name is kuma-defuzex; Python imports and the CLI remain kuma. For optional OTel dependencies and Trace setup, see the Runtime Trace guide.

Versions and update reminders

SDK version: 0.2.5. Publication status is shown in the official Releases. Run kuma updates check (or Python kuma.check_for_updates()) to check stable Release tags: patch-only updates are optional, higher major/minor versions require an upgrade reminder, but never block work or install automatically. Official requests check in the background; import/help/local/custom do not. Set KUMA_DISABLE_UPDATE_CHECK=1 to disable all checks. Offline failures are safe; results are cached for 24 hours per process. Old 0.1.0 users must upgrade manually once to gain reminders. Full policy and limits.

Quick start

Run the deterministic local check without an account, API key, Docker, or network:

kuma quickstart

Full-stack user-flow example

Follow the full-stack user-flow guide to run KUMA with mini-SWE-agent in Docker. This path calls external services and may use service credit and model budget.

Detailed documentation

Save and reuse a Case

Runtime Trace and optional file diffs

English SDK guide · Strategy Groups · Agent tool capabilities · Python API reference · Agent Profile migration · 简体中文 SDK 指南 · 中文 API 参考 · Runtime Evidence contract

Project

Security · Contributing · Apache License 2.0

Metadata

Release files for kuma-defuzex 0.2.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kuma-defuzex 0.2.5
File Size Uploaded
kuma_defuzex-0.2.5.tar.gz 230.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for kuma-defuzex 0.2.5
File Interpreter ABI Platform
kuma_defuzex-0.2.5-py3-none-any.whl Python 3 none any Details

Total release size: 501.1 kB

Release files / kuma_defuzex-0.2.5.tar.gz

Download URL kuma_defuzex-0.2.5.tar.gz
Size 230.2 kB
Tags Source
SHA-256 checksum
How to use checksums
96cb1105423765e5b7babe1b1abf6b62969a23e1f3df0f888f4a102840b24529
BLAKE2b-256 checksum
How to use checksums
4a1c69575721201388e35cbb02f883c518d02323279e92205d97eedc37034f72
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 15, 2026.

Transparency log

Release files / kuma_defuzex-0.2.5-py3-none-any.whl

Download URL kuma_defuzex-0.2.5-py3-none-any.whl
Size 270.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fd367a865b1adbb94d84466ffcf9bbb7b675b362ca67f75b394ec773a49b4a33
BLAKE2b-256 checksum
How to use checksums
3694a1089d381fa0e69da753b5e7a156257561f549498c3b668301c68d03c446
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 15, 2026.

Transparency log

Release history Release notifications | RSS feed

0.3.3

2 release files

0.3.2

2 release files

0.3.1

2 release files

0.3.0

2 release files

0.2.8

2 release files

0.2.7

2 release files

0.2.6

2 release files

This release

0.2.5 This release

2 release files

0.2.4

2 release files

0.2.3

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page