Skip to main content

Python SDK for the ACR (Agent Composition Records) network

Project description

tethral-acr

Python SDK for the ACR (Agent Composition Records) network.

Install

pip install tethral-acr

Quick Start

from tethral_acr import ACRClient

with ACRClient() as acr:
    # Register
    result = acr.register(
        public_key="your-unique-key-at-least-32-chars-long",
        provider_class="langchain",
    )
    agent_id = result["agent_id"]

    # Log an interaction
    acr.submit_receipt({
        "emitter": {"agent_id": agent_id, "provider_class": "langchain"},
        "target": {"system_id": "api:openai.com", "system_type": "api"},
        "interaction": {
            "category": "tool_call", "status": "success",
            "duration_ms": 800, "request_timestamp_ms": 1711978987442,
        },
        "anomaly": {"flagged": False},
    })

    # See what's costing you the most
    report = acr.get_friction_report(agent_id, scope="day")

API

Method Description
register(public_key, provider_class, ...) Register an agent
submit_receipt(receipt) Submit a single receipt
submit_receipts(receipts) Submit a batch (max 50)
update_composition(agent_id, ...) Update skill composition
check_skill(skill_hash) Check a skill before installing
check_agent(agent_id) Look up an agent
get_system_health(system_id) Get system health
get_active_threats() Get current threats
get_friction_report(agent_id, scope) Friction analysis
health() API health check

Data Collection

ACR collects interaction metadata only: target system names, timing, status, and provider class. No request/response content, API keys, prompts, or PII is collected. Full terms.

License

MIT

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

tethral_acr-0.1.0.tar.gz (4.5 kB view details)

Uploaded Source

Built Distribution

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

tethral_acr-0.1.0-py3-none-any.whl (4.8 kB view details)

Uploaded Python 3

File details

Details for the file tethral_acr-0.1.0.tar.gz.

File metadata

  • Download URL: tethral_acr-0.1.0.tar.gz
  • Upload date:
  • Size: 4.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for tethral_acr-0.1.0.tar.gz
Algorithm Hash digest
SHA256 213f4f06cc9fc7389acd54bff2edc6b7299e41d9874ccd420cb158c26dc1ddbc
MD5 c7403315db052785f10fe6d84b59dd0a
BLAKE2b-256 3f55356e0a82164eee99a5f31a7b0c841bda6885da55106300459a905c4d2c82

See more details on using hashes here.

File details

Details for the file tethral_acr-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: tethral_acr-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 4.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for tethral_acr-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 394298c3e54877e3a5be011648cf67eb55ecb5af5c1c5184a1adef13587e3389
MD5 deb3bbbbe19f04a5984eeb703e733524
BLAKE2b-256 5ad4fb6e41120d0c8dfb16cc49c366c0a7869f53389419a22abc81f931c620d8

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