API

Build with the Agenta API

Everything the app does, the REST API does: create agents, commit revisions, run evaluations, and read traces. The full specification is published at /openapi.json.

Base URL and authentication

Cloud (US): https://us.cloud.agenta.ai/api
Cloud (EU): https://eu.cloud.agenta.ai/api
Self-hosted: $AGENTA_HOST/api
Authorization: Authorization: ApiKey $AGENTA_API_KEY

An API key is scoped to a single project, so endpoints take no project_id. Create one in your project settings on Agenta Cloud.

Example request

curl -X POST "https://us.cloud.agenta.ai/api/simple/workflows/query" \
  -H "Content-Type: application/json" \
  -H "Authorization: ApiKey $AGENTA_API_KEY" \
  -d '{}'

What Agenta is for

Build an agent from a plain-language description, then improve it with feedback from real runs.
Version prompts, skills, and tools like code, and roll back to any earlier revision.
Evaluate a change against a test set before it ships, with LLM-as-a-judge or your own evaluators.
Trace every run to see each step, its cost, and where it failed.
Run an agent on a schedule, or when an event happens in a connected app.
Put a human approval step in front of consequential actions.

Reference

OpenAPI 3.1 specification — every endpoint, machine-readable.
Documentation — guides, the endpoint reference, and SDK usage.
llms.txt — a short map of this site for agents, including when to reach for Agenta.

Python SDK: pip install agenta.