Skip to main content

tethered-trust (Python)

Fit, compatibility and recall checks for AI agents before they buy. Every answer is a decision (supported, conditional, incompatible, insufficient_evidence) with the rules checked, manufacturer sources and a signed receipt.

  • Standard library only (Python 3.8+)
  • Tool definitions for OpenAI, Anthropic and LangChain
  • Same tools as the Tethered Trust MCP server (https://tetheredtrust.com/mcp)
pip install tethered-trust            # add [langchain] for LangChain tools

Quick start

from tethered_trust import TetheredTrust

tt = TetheredTrust(sandbox=True)  # sandbox: free, never charged
cart = tt.check_cart({
    "owned": ["Sony PlayStation 5 Pro"],
    "line_items": [{"id": "li_1", "title": "Samsung 990 PRO with Heatsink 2TB", "quantity": 1}],
})
if cart["safe_to_checkout"]:
    # place the order, then link the receipt to it (free)
    tt.call("attach_order", {"receipt_id": cart["receipt"]["id"], "order_id": "112-5550001"})
else:
    print(cart["action"], cart["questions"])

Drop sandbox=True for live answers. Without a key you get a small free daily allowance; after that use an API key with prepaid credits (TetheredTrust(api_key="tt_..."), buy at tetheredtrust.com/credits) or pay per answer in USDC with x402.

Give the tools to your model

from openai import OpenAI
from tethered_trust import TetheredTrust, to_openai_tools, run_tool, SHOPPING_TOOLS

tt = TetheredTrust(api_key="tt_...")
res = OpenAI().chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Will this charger work with my Pixel 10? Anker Nano Charger 30W"}],
    tools=to_openai_tools(SHOPPING_TOOLS),
)
for call in res.choices[0].message.tool_calls or []:
    print(run_tool(tt, call.function.name, call.function.arguments))

Anthropic: to_anthropic_tools(SHOPPING_TOOLS) gives the tools list for client.messages.create(...); run each tool_use block with run_tool(tt, block.name, block.input).

LangChain: to_langchain_tools(tt, SHOPPING_TOOLS) returns StructuredTools you can bind to any chat model.

What to do with the answer

decision Do this
supported Proceed; relay caveats.
conditional Proceed only once every item in conditions is met.
incompatible Don't buy; use substitutions or fix_purchase_plan.
insufficient_evidence Ask the returned questions, then check again.

Keep the receipt; after ordering, attach_order makes it a Decision Record. If an answer was wrong, file_claim within 60 days refunds the fee.

Docs: https://tetheredtrust.com/agents · Pricing: https://tetheredtrust.com/pricing · Terms: https://tetheredtrust.com/api-terms

Answers are informational; confirm with the manufacturer before buying. MIT licensed. © Chimes In LLC.

Metadata

Release files for tethered-trust 0.1.0

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

Source distribution (sdist)

Source distribution for tethered-trust 0.1.0
File Size Uploaded Provenance Actions
tethered_trust-0.1.0.tar.gz 16.2 kB With provenance Details for tethered_trust-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for tethered-trust 0.1.0
File Interpreter ABI Platform Actions
tethered_trust-0.1.0-py3-none-any.whl Python 3 none any Details for tethered_trust-0.1.0-py3-none-any.whl

Total release size: 31.8 kB

Release files / tethered_trust-0.1.0.tar.gz

Download URL tethered_trust-0.1.0.tar.gz
Size 16.2 kB
Tags Source
SHA-256 checksum
How to use checksums
136e30831a5e753f71e243254c5f2fa375dd54fa6caca02008b27c5efcddd092
BLAKE2b-256 checksum
How to use checksums
af0c1615b86b51ca90508caa16ad944054f28f9247ae9f96823d3ba87d818b0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

Release files / tethered_trust-0.1.0-py3-none-any.whl

Download URL tethered_trust-0.1.0-py3-none-any.whl
Size 15.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8af5773f069379ce22375890d62f8c9726c0044e69a17d91f8bc6803804959b9
BLAKE2b-256 checksum
How to use checksums
7f303c6464e9ada2645bb77ff1d6a40557fa4c835ba8bada72af06864caa87ad
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

Security for tethered-trust 0.1.0

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for tethered_trust-0.1.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 8, 2026.

Transparency log

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.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files Full provenance

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