Skip to main content

auditail (Python SDK)

Controls and evidence for AI agents that move money. Limits agents can't change, human approval, a kill switch, and a signed, tamper-evident record of every decision.

📖 Full Documentation · 🚀 Join the Private Beta


Install

pip install auditail
pip install "auditail[verify]"   # adds verify_receipt() for the service that executes actions

Quickstart

from auditail import Auditail, rules

aegis = Auditail(api_key="your_key")

aegis.add_rules([
    rules.no_external_email(internal_domains=["acme.com"]),
    rules.no_data_deletion(),
])

result = aegis.guard(
    action="send_email",
    payload={"to": "client@example.com", "body": "Report attached."},
    agent_id="financial-bot-01",
)

if result.approved:
    send_email(...)
else:
    print(f"Blocked: {result.reason}")

LangChain Integration

from langchain.agents import tool
from auditail import Auditail, rules

aegis = Auditail(api_key="your_key")
aegis.add_rule(rules.no_external_email(internal_domains=["acme.com"]))

@tool
def send_email(to: str, body: str) -> str:
    """Send an email to a recipient."""
    result = aegis.guard(
        action="send_email",
        payload={"to": to, "body": body},
        agent_id="langchain-agent",
    )
    if not result.approved:
        return f"Action blocked by Auditail: {result.reason}"
    # ... actual send logic
    return "Email sent."

Private beta

The SDK, API and dashboard are live. Guardrail rules run locally in your process; every decision is delivered in the background to a hash-chained audit log you can browse and verify at app.auditail.io.

  • Batched, retried, idempotent delivery. guard() never waits on the network, and a delivery failure never reaches your agent.
  • Secrets are redacted before an event leaves your process (password, token, apiKey, ... plus your own redact_keys).
  • Call aegis.flush() before a serverless function returns or the process exits.

Request an API key: keys are issued to design partners personally.

Human approval is live: a require_approval rule pauses the agent until someone approves or denies it in the dashboard or through your webhook (Slack, Teams, Discord, any HTTPS endpoint). No answer means denied. See the approval guide.

Server-side policies: allowed actions with everything else denied, spending and rate limits counted atomically on the server, rules for data from untrusted sources, and reason codes with hints the agent can act on. Approvers write them; agents can't change them. See policies.

Signed receipts: every human approval returns a receipt your payment or email service can verify before acting (verifyReceipt), so an agent cannot skip the check. Logs export to a file anyone can verify offline: npx -p auditail-sdk auditail-verify. See receipts and evidence.

Roadmap (not available yet): native Slack and PagerDuty apps, private-cloud deployment.

License

MIT

Metadata

Release files for auditail 0.6.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for auditail 0.6.0
File Size Uploaded Provenance Actions
auditail-0.6.0.tar.gz 20.0 kB Without provenance Details for auditail-0.6.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for auditail 0.6.0
File Interpreter ABI Platform Actions
auditail-0.6.0-py3-none-any.whl Python 3 none any Details for auditail-0.6.0-py3-none-any.whl

Total release size: 38.0 kB

Release files / auditail-0.6.0.tar.gz

Download URL auditail-0.6.0.tar.gz
Size 20.0 kB
Tags Source
SHA-256 checksum
How to use checksums
3de5dc81601a2ac77e6ec5d7581153e0f70326c5a7c153a4074306a7dced69d2
BLAKE2b-256 checksum
How to use checksums
3f826f866c3c76fc54ba849d761e19584d0e3d6fa6f8c44c02ad38c12c205ddf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release files / auditail-0.6.0-py3-none-any.whl

Download URL auditail-0.6.0-py3-none-any.whl
Size 18.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
e1ef8d3c5873bb497e31348bb208302ed66039569a602c4d245f13b4d4dc31ad
BLAKE2b-256 checksum
How to use checksums
b7188b0b5569a5892a79ba047a533d32e0e6f811951e123c4536d83e66df04a1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Security for auditail 0.6.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page