Skip to main content

Server for Agent Control - manage and evaluate controls for AI agents

Project description

Agent Control Server

FastAPI server that powers Agent Control. It manages agents and controls, evaluates requests at runtime, and exposes REST APIs used by the SDKs and UI.

What it provides

  • Agent registration and control association
  • Control CRUD and evaluator configuration
  • Runtime evaluation (/api/v1/evaluation) with pre/post stages
  • Observability endpoints for events and stats
  • API key authentication for production deployments

Quick start (local)

From the repo root:

make sync
make server-run

Server runs on http://localhost:8000. The UI expects this base URL by default.

To use non-default local ports with make server-run, export AGENT_CONTROL_PORT for the server listen port. If you also want the local Postgres container exposed on a different host port, set AGENT_CONTROL_DB_HOST_PORT and point the server at the same value with AGENT_CONTROL_DB_PORT.

Configuration

Server configuration is driven by environment variables (database, auth, observability, evaluators). For the full list and examples, see the docs.

Full guide: https://docs.agentcontrol.dev/components/server

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_control_server-7.7.0.tar.gz (248.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_control_server-7.7.0-py3-none-any.whl (173.4 kB view details)

Uploaded Python 3

File details

Details for the file agent_control_server-7.7.0.tar.gz.

File metadata

  • Download URL: agent_control_server-7.7.0.tar.gz
  • Upload date:
  • Size: 248.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for agent_control_server-7.7.0.tar.gz
Algorithm Hash digest
SHA256 b9bf66451a06da35f186591ec8467982d6e958f00b42ba1ff448773faf639bdb
MD5 e4212e26e5b550ee9d844343b67579a4
BLAKE2b-256 88fdef893ac94c1ecfe548288eefb7ef73f74d9ffd07801d4c2666730a13dd92

See more details on using hashes here.

File details

Details for the file agent_control_server-7.7.0-py3-none-any.whl.

File metadata

File hashes

Hashes for agent_control_server-7.7.0-py3-none-any.whl
Algorithm Hash digest
SHA256 bfd05de5c0bfc9cf73c40e943df783e6fb6f1538f6b41559dfb6ffd0ef3c9e2f
MD5 8e8d732e5493b634b28418019a8ca34b
BLAKE2b-256 5baa620641f5669a61dcbc248a3bd87259edf487a9a70fffd797abd1685ddcbe

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page