# OranAi-Ltd/oransim

Causal Digital Twin for Marketing at Scale · Predict any marketing decision before you spend a dollar.

Repository: https://github.com/OranAi-Ltd/oransim
Canonical: https://ross.abutalabs.com/products/oransim
Homepage: https://oran.cn
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-17T17:47:58+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 93, release rhythm 35, longevity 9
- inputs: {"age_days": 137, "days_push": 47, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1073, forks 133 (observed 2026-08-28T04:03:28.909822+00:00)

## What it is
Oransim is an open-source causal digital twin engine for marketing, simulating a large virtual consumer society with LLM-backed personas to predict campaign ROI and run counterfactual what-if analyses before spending budget. The public repo runs the same causal engine on a demo corpus, with licensed access to larger proprietary creator and consumer datasets offered commercially.

## Use cases
- predict marketing campaign roi before spending
- simulate consumer response to ad creatives
- run counterfactual what-if analysis on marketing decisions
- model an agent-based virtual consumer society
- audit causal logic behind marketing predictions
- test campaign strategies against simulated personas
- estimate creator marketing impact on social platforms

## When to choose
- you want to forecast campaign outcomes and ROI before committing budget
- you need transparent, auditable causal simulation logic rather than a black-box model
- you work with Chinese social platforms like Xiaohongshu and want creator/note-level analysis
- you want an open-source engine you can extend with your own data

## When to avoid
- you need production-grade licensed data on millions of creators, which requires commercial access
- you expect a polished end-user GUI product rather than a Python engine
- your marketing channels are unrelated to the platforms covered by the demo corpus
- you need guaranteed prediction accuracy for small-sample or novel markets

## Facets
- artifact type: library
- maturity: active
- function: simulation, machine-learning, agent-framework, data-science, analytics
- domain: artificial-intelligence, machine-learning, analytics, simulation, data-science
- platform: python, cross-platform, cli
- tags: digital-twin, causal-inference, marketing-analytics, agent-based-simulation, counterfactual-reasoning, llm-personas, roi-prediction, campaign-simulation, social-media-analytics, xiaohongshu, marketing

## Member repositories
- OranAi-Ltd/oransim (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.909822+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:35.222784+00:00, confidence not recorded.
  - readme: https://github.com/OranAi-Ltd/oransim (fetched 2026-08-28T04:03:28.909822+00:00, sha a4d6f016ab69)
  - homepage: https://oran.cn (fetched 2026-08-29T12:55:38.759792+00:00, sha a0a138fab9df)
- Data as of 2026-08-30T08:39:29.467469+00:00.