lightningrod-python-sdk

Lightningrod Python SDK — forecasting inference skills

CLEARED_STATICclaude-onlyv1.0.0

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

Claude-only

Type

Plugins

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocran3626 code lines / 36 files

secretsranno secret patterns matched

egressranno egress patterns matched

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraldeferredbehavioural assessment deferred (v1): Python with non-stdlib imports (committed-only policy): [('tests/test_inference_e2e.py', 'lightningrod'), ('tests/test_inference_e2e.py', 'pytest')]

What's inside

Components found

docs/forecasting/agentic-payments.md

agentmedium

docs/forecasting/openai.md

componentlow

docs/forecasting/quickstart.md

componentlow

docs/forecasting/recipes.md

componentlow

docs/forecasting/sdk.md

componentlow

docs/platform/overview.md

componentmedium

skills/verify-forecasting-docs/SKILL.md

skillhigh

Coverage

Not assessed

behavioural execution not run

README

From the repository

![](https://github.com/user-attachments/assets/66056c7a-6c6e-4040-a1a0-9852f709a0c5)


# Lightning Rod Python SDK

**Foresight** returns a calibrated probability for any question about the future through an OpenAI-compatible API.

**Trusted for high-stakes predictions** by Numinous, Shore Capital Partners, Awardable, ERIS Marketplace, and others. Foresight processes **billions of tokens** and serves **100k+ inference requests every day**.

[Documentation](https://docs.lightningrod.ai/) · [Get an API key](https://dashboard.lightningrod.ai/sign-up?redirect=/api) · [Research paper](https://arxiv.org/abs/2601.06336)

## ⚡ Better AI Predictions

Foresight is served behind an OpenAI-compatible endpoint, so any OpenAI client works — just point `base_url` at Lightning Rod.

```python
from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.lightningrod.ai/v1/openai",
)

completion = client.chat.completions.create(
    model="foresight-v4",
    messages=[
        {"role": "user", "content": "Will the Fed cut rates at its next meeting?"},
    ],
    extra_body={"research": True}, # Auto research the most relevant prediction context
)

print(completion…

← Back to Plugins