Skip to main content

Harnessed

A Python agent SDK built from reversible plugins. Harnessed owns the loop, tool policies and append-only session log; optional provider integrations use PydanticAI's Direct API. Python 3.12-3.14, Pydantic v2 and modern generics.

Harnessed 0.1.x is alpha software. APIs and persisted session formats may change in minor releases before 1.0. See the release notes and compatibility policy.

Core SDK

uv add "harnessed[openai]"
import asyncio
from harnessed import Agent, Plugin, tool


class Calculator(Plugin):
    @tool(readonly=True)
    async def add(self, a: int, b: int) -> int:
        """Add two integers."""
        return a + b


agent = Agent(
    model="deepseek:deepseek-chat",  # DEEPSEEK_API_KEY
    instructions="Keep answers concise.",
    plugins=[Calculator()],
)


async def main():
    async with agent.session() as session:
        result = await session.run("What is 19 + 23?")
        print(result.text)


asyncio.run(main())

Agent has three configuration inputs: model, instructions, and plugins. It is reusable; each session owns its runtime and plugin lifetimes.

  • Composition: tools, policies and capabilities are plugins. Slots replace defaults, and agent.plugins shows the resolved composition.
  • Ownership: removing a plugin removes its registrations and effects. Explicit needs suspend and rebuild dependent plugins as services change.
  • Context: instructions and plugin guidance are fixed per session; named context values and steering supply changes during a run.
  • History: immutable events are the source of truth. Persistence, replay, forks and control outcomes use the same append-only log.

Test without credentials

from harnessed.testing import ScriptedModel, assert_tool_called, call, reply

model = ScriptedModel([call(Calculator.add, a=19, b=23), reply("42")])
agent = Agent(model=model, plugins=[Calculator()])

# Inside an async function:
# result = await agent.run("Add 19 and 23")
# assert_tool_called(result, "add", a=19, b=23)

Read by topic

Start with the documentation index or the SDK reference.

The standalone harnessed.kernel uses only the standard library. Optional features live under harnessed.plugins; providers live under harnessed.models.

Inspired by DeepSeek Harness and Cordis.

Released under the MIT License.

Metadata

Release files for harnessed 0.1.0

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

Source distribution (sdist)

Source distribution for harnessed 0.1.0
File Size Uploaded Provenance Actions
harnessed-0.1.0.tar.gz 133.9 kB With provenance Details for harnessed-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for harnessed 0.1.0
File Interpreter ABI Platform Actions
harnessed-0.1.0-py3-none-any.whl Python 3 none any Details for harnessed-0.1.0-py3-none-any.whl

Total release size: 299.9 kB

Release files / harnessed-0.1.0.tar.gz

Download URL harnessed-0.1.0.tar.gz
Size 133.9 kB
Tags Source
SHA-256 checksum
How to use checksums
afe221fbca27e34b38a6bcde331b14703e9ba013dd0cc9a9e1757a8cc3d225ce
BLAKE2b-256 checksum
How to use checksums
f2740b5bc94655a978766b1559089f6bdd78eb7f04ef61f2313a92a0479b79e6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 29, 2026.

Transparency log

Release files / harnessed-0.1.0-py3-none-any.whl

Download URL harnessed-0.1.0-py3-none-any.whl
Size 165.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1cdbfe48f58255b0edce0cf9625800f1b9ad6c223e4b3e5b7bbafb5bf69569c2
BLAKE2b-256 checksum
How to use checksums
6f15957eddc7e78a8e49e7bfe165dc7d77822bd4852541c2daf85cbe82693582
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Oct 29, 2026.

Transparency log

Security for harnessed 0.1.0

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for harnessed-0.1.0.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 Oct 29, 2026.

Transparency log

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.

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