Agent Harness

Harness (a13n-harness) is the embeddable execution SDK behind Harness UI and Service. It builds reusable agents, runs them with current tools and Environments, streams observations, and returns state for continuation. Start with the offline quickstart; the Python import is a13n_harness.

Capability composition

Build an AgentSpec with only the behavior your application needs. For example, to expose Environment tools and working state:

from a13n_harness import AgentSpec, HarnessBuilder
from a13n_harness.capabilities import WorkingStateCapability
from a13n_harness.environment import DynamicEnvironmentCapability, DynamicEnvironmentConfiguration

executable = HarnessBuilder().build(
    AgentSpec(model="openai-responses:gpt-5"),
    output_type=str,
    capabilities=(
        DynamicEnvironmentCapability(DynamicEnvironmentConfiguration()),
        WorkingStateCapability(),
    ),
)

Supply a fresh Provider Environment to each run(..., environment=...), or use environments={...} for named mounts. Harness enters and closes adapters; your application selects their configuration, current state, access policy, and when to destroy a backing target. See Environments and Capabilities.

Model construction

Pass a native model directly through HarnessBuilder.build(model=...), or select one in AgentSpec.model. a13n_harness.infer_model() constructs a model from supported aliases and caller-owned provider factories. create_model_http_client() builds a caller-owned httpx2 client for provider requests. Configure credentials and close owned clients in your application. See Models and Model authentication.

Execution boundary and filters

Each built Agent includes the tool execution boundary, message integrity filter, and request-only image preparation. Image preparation splits tall static images, compresses images to encoded-byte and dimension limits, and retains the newest images without changing saved history or original files. Configure the selected model's HarnessModelCharacteristics.image_input with ImageInputPolicy, or set image_input=None to disable automatic preparation. See Context.

Add Capabilities for policy, context, memory, delegation, or model recovery. Toolsets are available from a13n_harness.toolsets, and managed tool contracts from a13n_harness.tools.

A completed Run returns a HarnessState with a stable thread_id. Pass it as previous_state to continue the Thread; each new Run receives a fresh run_id. The Host persists accepted state and reconstructs credentials and other current authority on resume. State and resume covers serialization and interrupted calls.

Runnable examples and guides

Agent application: offline streaming turns, checkpointing, and restart recovery.
Environment Providers: construction, re-entry, and lifecycle.
Plugins and extensions: packaged middleware, Capabilities, and Environment integrations.
Harness guide: the public API by task.

Versioning

Harness and a13n-stream-protocol publish together at one exact version. Harness UI releases independently. The Harness specification owns the accepted contracts.

Metadata

Release files for a13n-harness 0.5.0

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

Source distribution (sdist)

Source distribution for a13n-harness 0.5.0
File	Size	Uploaded
a13n_harness-0.5.0.tar.gz	1.0 MB	Oct 1, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for a13n-harness 0.5.0
File	Interpreter	ABI	Platform	Reset
a13n_harness-0.5.0-py3-none-any.whl 787.2 kB Oct 1, 2026	Python 3	none	any	Details

Total release size: 1.8 MB

Release files / a13n_harness-0.5.0.tar.gz

Download URL	a13n_harness-0.5.0.tar.gz
Size	1.0 MB
Tags	Source
SHA-256 checksum How to use checksums	`9a75ff8b36f0533a20d6dd3eb01a9c23d8ee4901506cdc583d0868fa8a5d39bc`
BLAKE2b-256 checksum How to use checksums	`76a4c949edf86fa4193a7dc936c33f6abe104f9bb46455e825613676493162d8`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Release files / a13n_harness-0.5.0-py3-none-any.whl

Download URL	a13n_harness-0.5.0-py3-none-any.whl
Size	787.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`be18ccddf16a88dfca6a11c51997519078ea8ca84ce1a7b51c1de8ab3c353148`
BLAKE2b-256 checksum How to use checksums	`99a4ab2300ea3c11ade76812d9a145681d4683204c49de2a39fd7a5724a2c9b7`
Upload date	Oct 1, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.21 {"installer":{"name":"uv","version":"0.12.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`