Registry / llm-agents / tensorzero

tensorzero

JSON →
library2026.5.0pypypi✓ verified 34d ago

The Python client for TensorZero, an open-source platform for optimizing and evaluating LLM applications. Current version 2026.5.0, requires Python >=3.10. Released approximately monthly.

llm-agentsai-mlobservability
Install & Compatibility
Where this runs

No compatibility data collected yet for this library.

Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

The main client class was historically named 'Client' but is now 'TensorZeroGateway' in modern versions.

from tensorzero import TensorZeroGateway

Direct import of inference function

from tensorzero import inference

Initialize TensorZero client and make a simple inference.

from tensorzero import TensorZeroGateway # Initialize client pointing to your TensorZero gateway client = TensorZeroGateway(base_url='http://localhost:3000') # Make an inference response = client.inference( function_name='chatbot', input={ 'messages': [ {'role': 'user', 'content': 'Hello!'} ] } ) print(response['output']['content'])
Debug
Known footguns
breakingVersion 2026.5.0 changes UI authentication: when gateway requires auth, UI now also requires auth.
breakingVersion 2026.4.1 defaults to async observability writes, reducing tail latency.
breakingVersion 2026.2.2 changes config-file globbing: single-level wildcards no longer match across directories.
breakingVersion 2026.2.1 changes default `cache_options.enabled` from `write_only` to `off`.
deprecatedLegacy inference evaluations format (flat under `[evaluators]`) is deprecated since 2026.3.4.
deprecatedThe `model_provider_name` filter for `extra_body` and `extra_headers` was removed in 2026.3.1.
Upgrade
Version history

Breaking-change detection hasn't run for this library yet.

Audit
Security & dependencies

CVE tracking and dependency tree are planned for a later release.

Agent activity
0 hits · last 30 days

No traffic data recorded yet.

Resources