Polanyi

Synthetic shoppers hard-pinned to any website → recommendation-system event logs.

Point Polanyi at a URL. It runs a diverse set of Nemotron personas as on-site shoppers (search, compare, select, stop before PII/payment) and emits privacy-safe recsys_events for offline experiments.

Install

pip install polanyi

From source:

cd polanyi_agent_harness
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

Colab / product path (POLANYI_API_KEY)

1. Sign up at https://polanyilabs.com/signup, verify your email, and create a key in the dashboard.
2. In Colab:

!pip install -q "polanyi>=0.4"

import os
os.environ["POLANYI_API_KEY"] = "pk_live_..."  # from your dashboard

from polanyi import Client
result = Client().simulate(site="https://www.nike.com", n=3, concurrency=3)
print(result.summary())
result.to_jsonl("nike_events.jsonl")

Local / power-user path (BROWSER_USE_API_KEY)

cp .env.example .env
# BROWSER_USE_API_KEY=bu_...

from polanyi import Client

client = Client()  # uses Browser Use Cloud directly
result = client.simulate(
    site="https://www.expedia.com",
    n=10,
    concurrency=5,
    output_dir="runs/expedia",
)
print(result.summary())
result.to_jsonl("runs/expedia/merged.jsonl")

Agents are hard-pinned: they start on your site and must not leave that domain. External “Book with…” handoffs stop with checkout_boundary_stop (first-party-shaped data).

Accounts and API keys

Accounts, keys and usage live in Supabase (schema: supabase/migrations/ in the website repo).

1. Users sign up on the website (email + password with a 6-digit verification code, or Google).
2. In the dashboard they create, name and revoke pk_live_… keys. A key is shown once; only its SHA-256 hash is stored.
3. This server authorizes each request with the Supabase service-role key, enforces the user's monthly_persona_limit (default 100 personas/month), and records every simulation in usage_records. Simulations are private to the account that created them.

Server env (Fly):

fly secrets set -a polanyi \
  SUPABASE_URL="https://<project>.supabase.co" \
  SUPABASE_SERVICE_ROLE_KEY="<service_role key>" \
  POLANYI_DAILY_PERSONA_CAP=300

POLANYI_DAILY_PERSONA_CAP is a global safety limit across all users (optional). To raise one user's quota, edit profiles.monthly_persona_limit in the Supabase table editor.

Legacy: POLANYI_API_KEYS (comma-separated) and POLANYI_ADMIN_TOKEN + POST /v1/admin/keys still work for internal keys stored in POLANYI_DATA_DIR/api_keys.json.

Docker:

docker build -t polanyi-api .
docker run --rm -p 8080:8080 \
  -e POLANYI_API_KEYS=pk_live_... \
  -e BROWSER_USE_API_KEY=bu_... \
  polanyi-api

API surface:

Method	Path	Purpose
GET	/health	Liveness
POST	/v1/simulations	Start a job (Bearer pk_…)
GET	/v1/simulations/{id}	Poll status + events

CLI

# Any site, N diverse personas
polanyi-sim --site https://www.nike.com --batch 5 --concurrency 5 \
  --output-dir output/nike_run

# Optional journey brief
polanyi-sim --site expedia.com --batch 10 --concurrency 10 \
  --prompt "Browse hotels and flights; pick what fits your budget." \
  --output-dir output/expedia_run

# Dry-run (personas only, no Browser Use)
polanyi-sim --site example.com --batch 3 --dry-run-persona --output-dir output/dry

Legacy (no --site) still works but is not hard-pinned.

Outputs

Each session directory contains:

File	Purpose
persona.json	Synthetic identity
browser_use_raw.json	Raw Browser Use run
recsys_events.jsonl / .parquet	Ordered recsys events
simulate_meta.json	Site + run config (SDK / --site runs)
simulate_plan.json	Inferred vertical + per-persona journey goals

How journeys are planned

Live runs (Client.simulate / polanyi-sim --site without --dry-run-persona):

1. LLM diagnosis — a Browser Use agent opens the real site and returns an accurate JSON profile (site_name, vertical, description, journey_templates)
2. Saved to simulate_diagnosis.json
3. Each persona gets a different template from that diagnosis, personalized with their location/budget

Dry-runs skip the LLM and fall back to URL heuristics only.

from polanyi import diagnose_site, plan_journeys
from polanyi.personas import load_personas

diagnosis = diagnose_site("https://www.ticketnetwork.com")
print(diagnosis.site_name, diagnosis.vertical)
print(diagnosis.description)
plan = plan_journeys("https://www.ticketnetwork.com", load_personas(count=3), diagnosis=diagnosis)

Safety

• Synthetic actor IDs only (syn_nmusa_*)
• training_use=offline_sandbox_only
• Hard stop before identity / payment
• Hard site pin (first-party shaped)

Publish to PyPI

pip install build twine
python -m build
twine upload dist/*

The polanyi name is available on PyPI as of packaging time.

Roadmap

1. Schema, personas, Cloud runner, batch concurrency
2. Python SDK Client.simulate(site=…) + hard pin
3. LLM site diagnosis → diverse per-persona journeys
4. POLANYI_API_KEY + self-hostable API wrapping Browser Use
5. Parse quality gates + JSON repair for agent output
6. Hosted api.polanyi.ai + public PyPI release