Trajectory SDK

Generated Python client for the Trajectory API, with high-level workflows for uploading trajectories, telemetry, and runtime-backed benchmarks.

Install

pip install trajectory-sdk

Install the optional agent and Harbor integrations used by the full CLI with:

pip install "trajectory-sdk[cli]"

Quick start

Set TRAJECTORY_API_KEY, then create a client:

from trajectory import Client

client = Client()
benchmarks = client.benchmarks.list(limit=10)

The generated resource methods map directly to the public HTTP API. Higher-level operations that coordinate multiple API calls are available from trajectory.lib:

from trajectory import Client
from trajectory.lib import ingest_events

client = Client()
result = ingest_events(
    client,
    [
        {
            "event_type": "agent.completed",
            "session_id": "session-123",
            "timestamp": "2026-08-28T00:00:00+00:00",
            "properties": {"model": "example-model"},
        }
    ],
)
print(result.ingested, result.skipped)

LiteLLM harnesses

Starting with SDK 0.6.6, an existing LiteLLM harness can use this import for policy calls:

from trajectory.lib.litellm import completion

response = completion(model=model, messages=messages, temperature=1.0)

This always uses the injected Trajectory endpoint and credentials. Messages and tools are unchanged. Keep user/judge calls on native LiteLLM and retain the original loop and grader, then report their result with the existing client.trajectories.log_reward(...) and client.trajectories.complete(...) methods.

Command line

The package installs a handwritten trajectory command that delegates API operations to the same generated client and high-level workflows:

export TRAJECTORY_API_KEY="tj_key_..."

trajectory trajectories upload trajectories.json --dataset my-dataset
trajectory telemetry ingest events.json
trajectory traces upload trajectories.json --events events.json --dataset my-dataset
trajectory secrets set OPENAI_API_KEY
trajectory secrets list

API-backed commands use a 30-minute timeout by default. Override it with --timeout SECONDS. The existing repository and benchmark tools remain available from the new CLI package:

trajectory bench validate ./benchmark
trajectory bench push ./benchmark --build-images
trajectory extract harness

Development

uv run pytest
uv run ruff check .
uv run ruff format --check .

The generated client lives in src/trajectory/. Handwritten workflows live in src/trajectory/lib/, the handwritten CLI lives in cmd/trajectory/cli/trajectory_cli/, and tests live in tests/.

License

Apache 2.0

Release files for trajectory-sdk 0.6.10

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

Source distribution (sdist)

Source distribution for trajectory-sdk 0.6.10
File	Size	Uploaded
trajectory_sdk-0.6.10.tar.gz	113.0 kB	Sep 12, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for trajectory-sdk 0.6.10
File	Interpreter	ABI	Platform	Reset
trajectory_sdk-0.6.10-py3-none-any.whl 186.5 kB Sep 12, 2026	Python 3	none	any	Details

Total release size: 299.5 kB

Release files / trajectory_sdk-0.6.10.tar.gz

Download URL	trajectory_sdk-0.6.10.tar.gz
Size	113.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`d1503862dd61f92362f77bbc2d10b8cd4a897e796209d687ed9197eb47debcae`
BLAKE2b-256 checksum How to use checksums	`379fc39472dd9f9c04baff93d57e1c1bf852be8b3a93aa22ab9cfab7d7f4cc04`
Upload date	Sep 12, 2026
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.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Trajectorylabs/trajectory-platform
Publishing commit: github.com/Trajectorylabs/trajectory-platform/tree/71363f83cd8617d6dafddac5338cdfa268b26327

Workflow

Publishing configuration: github.com/Trajectorylabs/trajectory-platform/blob/71363f83cd8617d6dafddac5338cdfa268b26327/.github/workflows/publish-sdk.yml
Publishing logs: github.com/Trajectorylabs/trajectory-platform/actions/runs/34721745114/attempts/1

Artifact

Subject: trajectory_sdk-0.6.10.tar.gz
SHA-256 checksum: d1503862dd61f92362f77bbc2d10b8cd4a897e796209d687ed9197eb47debcae Verifying attestations

Release files / trajectory_sdk-0.6.10-py3-none-any.whl

Download URL	trajectory_sdk-0.6.10-py3-none-any.whl
Size	186.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`dd8a6303947fead3a1df0949244593fc146ff2f052dc196f28354be9585d5215`
BLAKE2b-256 checksum How to use checksums	`2871b99b8d22e2a569e886079df1e3be16a5ff9e833bdbf8accf37e49fec5221`
Upload date	Sep 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/Trajectorylabs/trajectory-platform
Publishing commit: github.com/Trajectorylabs/trajectory-platform/tree/71363f83cd8617d6dafddac5338cdfa268b26327

Workflow

Publishing configuration: github.com/Trajectorylabs/trajectory-platform/blob/71363f83cd8617d6dafddac5338cdfa268b26327/.github/workflows/publish-sdk.yml
Publishing logs: github.com/Trajectorylabs/trajectory-platform/actions/runs/34721745114/attempts/1

Artifact

Subject: trajectory_sdk-0.6.10-py3-none-any.whl
SHA-256 checksum: dd8a6303947fead3a1df0949244593fc146ff2f052dc196f28354be9585d5215 Verifying attestations