Encord Agents

Easily build agents for the Encord ecosystem. With just few lines of code, you can take automation to the next level.

python -m pip install encord-agents

Key features:

⚡ Easy: Multiple template agents to be adapted and hosted via GCP, own infra, or cloud.
⏩ Convenient: The library conveniently loads data via the Encord SDK upon request.
👨‍💻 Focused: With essential resources readily available, you can focus on what matters. Create agents with pre-existing (or custom) dependencies for loading labels and data.
🤏 Slim: the library is slim at it's core and should not conflict with the dependencies of most projects.

💡 For the full documentation and end-to-end examples, please see here.

For help choosing between an editor agent and a task agent, see the documentation. Runnable examples — Colab notebooks, GCP, FastAPI, Modal and Celery deployments, and pre-built containerised agents — live in examples/.

Here's how to build an Agent:

from uuid import UUID
from encord.objects.ontology_labels_impl import LabelRowV2
from encord_agents.tasks import Runner

runner = Runner(project_hash="<your_project_hash>")


@runner.stage("<your_agent_stage_uuid>")
def by_file_name(lr: LabelRowV2) -> UUID | None:
    # Assuming the data_title is of the format "%d.jpg"
    # and in the range [0; 100]
    priority = int(lr.data_title.split(".")[0]) / 100
    lr.set_priority(priority=priority)
    return "<your_pathway_uuid>"


if __name__ == "__main__":
    runner.run()

You can also inject dependencies:

from typing_extensions import Annotated

from encord.objects import LabelRowV2
from encord_agents.tasks import Runner, Depends

runner = Runner(project_hash="<your_project_hash>")

def my_custom_dependency(label_row: LabelRowV2) -> dict:
    # e.g., look up additional data in own db
    return db.query("whatever")

@runner.stage(stage="<my_stage_name>")
def by_custom_data(
    custom_data: Annotated[dict, Depends(my_custom_dependency)]
) -> str:
    # `custom_data` automatically injected here.
    # ... do your thing
    # then, return name of task pathway.


if __name__ == "__main__":
    runner.run()

Please visit our 📖 Documentation for a complete reference to how to use the agents library.

Release files for encord-agents 0.2.10

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

Source distribution (sdist)

Source distribution for encord-agents 0.2.10
File	Size	Uploaded
encord_agents-0.2.10.tar.gz	3.2 MB	Sep 23, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for encord-agents 0.2.10
File	Interpreter	ABI	Platform	Reset
encord_agents-0.2.10-py3-none-any.whl 85.4 kB Sep 23, 2026	Python 3	none	any	Details

Total release size: 3.3 MB

Release files / encord_agents-0.2.10.tar.gz

Download URL	encord_agents-0.2.10.tar.gz
Size	3.2 MB
Tags	Source
SHA-256 checksum How to use checksums	`04f419286e97ecadd2c58cae5e224a5d2e5dbd17b92d39dd8b6d0da1cde2ce52`
BLAKE2b-256 checksum How to use checksums	`2d019048bd418f9bb57a7b40b77680edaa262ef72d0560367dc327535ac82e01`
Upload date	Sep 23, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.7.12`

Release files / encord_agents-0.2.10-py3-none-any.whl

Download URL	encord_agents-0.2.10-py3-none-any.whl
Size	85.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d74384d28beeeddbe855c6aa24f1020d5805ec36e202022c053fd4989d308733`
BLAKE2b-256 checksum How to use checksums	`a7f34e2412dc20e4d0d3a22840df357c7002d1aeb040ee6307b541641c06632c`
Upload date	Sep 23, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.7.12`