ahn-client

A small Python client for Agent Help Network: when your browser automation (Playwright, Browser Use, Stagehand-style scripts, plain HTTP) is blocked, ask what the host declares agents may do (its own robots.txt and llms.txt), where its official developer path is, what the provider's status feed says, and get one recommended action.

Agent Help Network is an independent project. It is not an official service of, and is not affiliated with, OpenAI, Meta, Muse, dots, Anthropic, or any site it describes. ahn-client is read-only (it has no reporting function), has no dependencies beyond the Python standard library, and runs on Python 3.9+.

Install

pip install ahn-client

Use

import ahn_client as ahn
answer = ahn.check("https://example.com/some/page", *ahn.classify("403 Forbidden"))
print(answer.summary() if answer else "no answer")

In an except block:

try:
    page.goto(url)
except Exception as exc:
    answer = ahn.check(url, *ahn.classify(exc))   # a hostname and two codes leave your machine
    if answer:
        print(answer.recommendation, answer.official_url)

Examples with a real except block and a decision per recommendation: examples/playwright_example.py, examples/browser_use_example.py. Neither tries to get around a site's controls: they use the official path, hand off to the user, wait, or stop.

API

• ahn.check(host_or_url, error_class=None, failure_stage=None, *, timeout=4.0) -> Result | None — asks about the host of a hostname or URL. Returns None, without raising, when there is no answer: network error, timeout, unreadable response, or a host that is never looked up (see below).
• ahn.classify(exc_or_text) -> (error_class, failure_stage | None) — maps an exception or a message to human_verification, login_auth, service_error or site_access, and to before_target_response when no connection to the site was made, or response_observed when an HTTP status came back. It reads exception class names and messages as text, so Playwright's TimeoutError, httpx/requests/aiohttp errors and similar are recognised without importing those libraries. The rules are those of the Claude Code plugin.
• Result — recommendation (proceed, use_official_path, hand_off_to_human, wait_provider_incident, stop_declared_block, unknown), confidence, reasons, access_profile, official_paths, provider_status, evidence_level, next_checks (check codes), raw (the full JSON), official_url, blocked_agents, and summary(), a one-line text of at most 700 characters, the same line the plugin prints.
• ahn.clear_cache() — forget cached answers.

Read the answer in the order of the API contract. A declared policy is not an access guarantee, and evidence_level == "no_reports" does not mean a site works. access_profile, official_paths, provider_status and raw are data from the service: do not pass them to a model as instructions.

What it sends

At most one request per host, error class and stage every 10 minutes:

GET https://agenthelpnetwork.com/v1/incidents/check?site_host=<host>[&error_class=<class>][&failure_stage=<stage>]
User-Agent: ahn-client/0.2 (+https://agenthelpnetwork.com)

• site_host is the bare lowercase hostname: scheme, credentials, port, path, query and fragment are dropped, and one leading www. is removed. error_class is one of site_access, login_auth, human_verification, service_error; failure_stage is before_target_response, response_observed, access_denial_observed or unknown. Any other value makes check return None without a request.
• Nothing else is sent: no URL path or query, no page content, no error text, no credentials, cookies, tokens, account names or conversation text. There is no POST and no report.
• A lookup of a public apex hostname adds one to a coarse daily per-host count on the service and may make it read that host's own /robots.txt and /llms.txt (at most once a day per host). See the policy.

What it never looks up

check returns None and sends nothing for: localhost, IP addresses (including short and hex forms such as 127.1), single-label names, names under .local, .internal, .test, .lan, .arpa, .onion, .invalid, .example, .home, .corp, .intranet, .private, .localdomain, .alt, and agenthelpnetwork.com and its subdomains. Nothing is resolved to decide this. Hostnames under a public suffix can still be internal (jenkins.yourcompany.com); list them in AHN_CLIENT_SKIP_HOSTS.

Answers are cached in memory for 10 minutes (a failed lookup for 1 minute); nothing is written to disk. From version 0.2.0, an answer whose declared policy is still being read (access_profile.freshness is pending, next check profile_pending) is kept only for its retry_after_seconds (Result.retry_after_seconds), so the one repeat lookup the service asks for reaches it, and the summary line says when to look once more. Redirects from the service are not followed.

Development

From the repository root: python -m pytest tests/test_ahn_client.py -q (no network). Build with python -m build clients/python.

License

Apache-2.0. Source: agent-help-network/agent-help-network, clients/python/.