Skip to main content

Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach. Python port of @mukundakatta/agentguard.

Project description

agentguard-py

PyPI Python License: MIT

Network egress firewall for AI agents. Declarative allow/deny list of hosts your agent tools may reach. Zero runtime dependencies.

Python port of @mukundakatta/agentguard.

Install

pip install agentguard-py

Usage

from agentguard import policy, check, PolicyViolation

p = policy({
    "network": {
        "allow": ["api.openai.com", "*.anthropic.com"],
        "deny":  ["billing.openai.com"],
        "methods": ["GET", "POST"],
    },
})

decision = check(p, "https://api.openai.com/v1/chat", {"method": "POST"})
# Decision(action='allow')

decision = check(p, "https://evil.example.com/")
# Decision(action='deny', reason='not_in_allowlist', detail='evil.example.com')

Plugging into HTTP clients

check() is the decision primitive. Wrap your favorite HTTP client around it:

import httpx
from agentguard import policy, check, PolicyViolation

p = policy({"network": {"allow": ["api.openai.com"]}})

class GuardedClient(httpx.Client):
    def send(self, request, **kw):
        d = check(p, str(request.url), {"method": request.method})
        if d.action == "deny":
            raise PolicyViolation(d.reason, d.detail, str(request.url), request.method)
        return super().send(request, **kw)

Pattern matching

Pattern Matches
"api.openai.com" exact host
"*.example.com" example.com and any subdomain (api.example.com, *.api.example.com, ...)
"*" everything (handy as a catch-all in deny)

Deny rules win over allow rules.

API differences from the JS sibling

  • No firewall(spec, fn) -- Python doesn't have AsyncLocalStorage / a clean global-fetch monkey-patching equivalent. Wire check() into your HTTP client of choice (see above).
  • No wrap_fetch() for the same reason.
  • Policy, Decision, and the inner network/budget objects are immutable dataclasses.
  • budget.maxRequests is accepted as an alias for budget.max_requests for parity with the JS docs.

See the JS sibling's README for the full design notes.

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

agentguard_firewall-0.1.0.tar.gz (6.3 kB view details)

Uploaded Source

Built Distribution

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

agentguard_firewall-0.1.0-py3-none-any.whl (6.7 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: agentguard_firewall-0.1.0.tar.gz
  • Upload date:
  • Size: 6.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for agentguard_firewall-0.1.0.tar.gz
Algorithm Hash digest
SHA256 24cb420e0eb2e648f412931f69920575f6196d19d7d1260fc78010d85a69ab91
MD5 40a2c9f5db89d8161b6e64c1e50ad045
BLAKE2b-256 cde354c7d81232f3a0d618ac89d8289a90a577b9edd5dbec6105832cbe0ccdcd

See more details on using hashes here.

File details

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

File metadata

File hashes

Hashes for agentguard_firewall-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 086c1d49ba3bad3e7e7b9aab1082241a46abc47661fb4fd2b03a8cbd2263ca5a
MD5 338f5e27ff9078db7c858e4a0f37b98e
BLAKE2b-256 b9bd002cd3cf86833ea49ab5008c28d6915a71aa6a58e58d235b4a8ac657f6c0

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