This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Reason given by maintainers: Deprecated: package lacked the framework-specific integration its name implies. Use the strale REST API, MCP server, or straleio SDK instead.
openai-agents-strale
OpenAI Agents SDK integration for Strale — 250+ independently tested and scored business data capabilities for AI agents.
Strale provides IBAN validation, VAT validation, company data across 27 countries, sanctions screening, compliance checks (KYB, AML, GDPR), invoice extraction, SSL certificate checks, and more. Every capability is quality-scored with the Strale Quality Score (SQS).
Installation
pip install openai-agents-strale
Quick Start
Single Tool
from agents import Agent, Runner
from openai_agents_strale import create_strale_tool
validate_iban = create_strale_tool(
api_key="sk_live_...",
capability_slug="iban-validate",
)
agent = Agent(
name="IBAN Validator",
instructions="You validate IBAN numbers using the Strale API.",
tools=[validate_iban],
)
result = Runner.run_sync(agent, "Is DE89370400440532013000 a valid IBAN?")
print(result.final_output)
Multiple Tools
from agents import Agent, Runner
from openai_agents_strale import create_strale_tools
tools = create_strale_tools(
api_key="sk_live_...",
slugs=["iban-validate", "vat-format-validate", "sanctions-check"],
)
agent = Agent(
name="Compliance Agent",
instructions="You verify business data using Strale tools.",
tools=tools,
)
result = Runner.run_sync(agent, "Check if VAT number SE556703748501 is valid")
print(result.final_output)
Category Filter
from openai_agents_strale import create_strale_tools
# Load all compliance tools
tools = create_strale_tools(
api_key="sk_live_...",
categories=["compliance"],
)
Direct Client
from openai_agents_strale import StraleClient
client = StraleClient(api_key="sk_live_...")
# Execute a capability directly
result = client.run("iban-validate", {"iban": "DE89370400440532013000"})
print(result)
# List available capabilities
caps = client.list_capabilities(category="company-data")
for cap in caps:
print(f" {cap['slug']} — €{cap['price_cents']/100:.2f}")
Capability Categories
| Category | Examples |
|---|---|
| Company Data | swedish-company-data, german-company-data, uk-company-data (27 countries) |
| Compliance | sanctions-check, pep-check, adverse-media-check, vat-validate |
| Validation | iban-validate, vat-format-validate, lei-lookup, swift-validate |
| Finance | exchange-rate, invoice-extract, invoice-validate |
| Web Intelligence | ssl-check, dns-lookup, domain-reputation, seo-audit |
| Data Extraction | pdf-extract, web-extract, url-to-markdown |
Full list: strale.dev/capabilities
Free Tier
5 capabilities work without an API key or signup: email-validate, dns-lookup, json-repair, url-to-markdown, iban-validate.
MCP Alternative
If your agent framework supports MCP, you can use Strale's MCP server directly:
- Endpoint:
https://api.strale.io/mcp - Transport: Streamable HTTP
- npm package: strale-mcp
Trust & Quality
Every Strale capability has a quality score (SQS) combining:
- Quality Profile: correctness, schema compliance, error handling, edge cases
- Reliability Profile: availability, success rate, upstream health, latency
Scores and methodology: strale.dev/trust
Using Strale in agent system prompts
Add this to your OpenAI agent's instructions for automatic capability routing:
When you need to verify a business, validate an IBAN or VAT number, screen
against sanctions/PEP lists, extract data from a URL or document, or check
compliance — use your Strale tools. Call strale_search to find the right
capability, then call it by name. Returns structured JSON with quality scores.
250+ capabilities across 27 countries. Free tier: email-validate, dns-lookup,
json-repair, url-to-markdown, iban-validate (no API key needed).
Links
Metadata
Release files for openai-agents-strale 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| openai_agents_strale-0.1.1.tar.gz | 6.5 kB | Without provenance | Details for openai_agents_strale-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| openai_agents_strale-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for openai_agents_strale-0.1.1-py3-none-any.whl |
Total release size: 13.2 kB
Release files / openai_agents_strale-0.1.1.tar.gz
| Download URL | openai_agents_strale-0.1.1.tar.gz |
|---|---|
| Size | 6.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cd98a799cf727ebddb4ea79cca5b9ee7f5344d128bbcfa326e2a46e982acb2ef
|
|
BLAKE2b-256 checksum How to use checksums |
91be512a5f49436dcc6321e005c648ac8750c4fecb5fa4a773da4eead2dd631a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Release files / openai_agents_strale-0.1.1-py3-none-any.whl
| Download URL | openai_agents_strale-0.1.1-py3-none-any.whl |
|---|---|
| Size | 6.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
36c20fa34e2428cce3b72f46038c1c6d6d0031bec442d841e702c8125af9d000
|
|
BLAKE2b-256 checksum How to use checksums |
89d6bb2debb01a0f6def5bf0e1784f0391f71911a870b95d34aca541ac5bf474
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.12
|
Security for openai-agents-strale 0.1.1
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.