First Steps

Choose one route:

Route A — Use this website (Baseline Generator)

If you want real-time metrics without writing code, use the Baseline Generator.

• Open: /baseline-generator
• What you get: live SGI + Velocity plots, context phase (if enabled), per-turn telemetry, exportable JSON.
• Best for: collecting human sessions, validating the coherence region, quick demos.

Route B — Integrate via the SDK Service (recommended)

If you want to integrate semantic telemetry into your own app, call the hosted SDK Service via the thin client.

Install

pip install aicoevolution

Minimal example (thin client)

import time
from aicoevolution_sdk import AICoevolutionClient

sdk = AICoevolutionClient(base_url="https://sdk.aicoevolution.com")
sdk.auth = sdk.auth.__class__(user_api_key="aic_your_key_here")

conv = "demo_conv_001"

sdk.ingest(conversation_id=conv, role="user", text="What is semantic orbital mechanics?", timestamp_ms=int(time.time() * 1000))
data = sdk.ingest(
    conversation_id=conv,
    role="assistant",
    text="It models a conversation as an orbit around a context centroid.",
    timestamp_ms=int(time.time() * 1000),
)

print("SGI:", data.get("sgi_mean"))
print("Velocity:", data.get("angular_velocity_mean"))

Expected output (example)

SGI: 0.95
Velocity: 34.2

Standalone script (open source)

The reference standalone script is:

• MirrorMind/open_source/semantic_telemetry.py

It will be included in the public Paper 03 research repository.