OranAi-Ltd

OranAi-Ltd / oransim

Public

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

oran.cnoransim
48
9
100% credibility
Found Apr 19, 2026 at 48 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Oransim is an open-source causal simulation tool for predicting social media marketing campaign performance including ROI, engagement curves, and counterfactual scenarios.

How It Works

1
🔍 Discover Oransim

You hear about a free tool that lets you test ad campaigns on social media before spending money, predicting clicks, sales, and spread.

2
🚀 Get started easily

Download and launch it on your computer with a simple setup, no tech skills needed.

3
📝 Describe your campaign

Enter your ad creative, budget, platforms like TikTok or Instagram, and key influencers.

4
✨ See predictions instantly

Watch colorful charts show expected views, clicks, sales, ROI ranges, and how opinions spread among virtual users.

5
🔄 Test what-if changes

Slide budgets, swap creatives or influencers, and instantly see how results shift.

6
🧠 Get smart insights

Review user reactions, group chats, and tips on optimizing your plan.

✅ Launch with confidence

Armed with predictions and recommendations, you run your real campaign knowing the risks and rewards upfront.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 48 to 48 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is oransim?

Oransim builds a causal digital twin for social media marketing, letting you simulate ad campaigns and predict outcomes like impressions, clicks, conversions, and ROI before spending a dime. Feed it a creative, budget, KOL list, and platform split; in about 60 seconds, it spits out forecasts with uncertainty bands, counterfactuals (like "what if we swap the creative?"), and 14-day diffusion curves via Hawkes processes. Python-powered with a FastAPI backend, React-like frontend demo, and pluggable LLM providers for agent personas that react to your actual copy.

Why is it gaining traction?

It tackles real pain points in digital advertising causal inference—like treatment confounding, budget fatigue, and intervention-aware diffusion—that black-box regressors ignore, using structural causal models and agent simulations at scale. The quickstart runs offline with mock LLMs or live with OpenAI/Anthropic keys, shipping a pretrained LightGBM baseline on synthetic data for instant results. Extensible platform adapters (XHS, TikTok, Instagram) and API endpoints for counterfactuals make it a solid starting point over MMM tools or naive AutoML.

Who should use this?

Marketing data scientists testing campaign what-ifs, ad platform engineers prototyping causal simulators, or growth teams optimizing KOL mixes and budgets pre-launch. Ideal for anyone in digital advertising needing causal digital twins to compare scenarios without real spend.

Verdict

Worth cloning for the demo—quickstart delivers playable predictions out of the box—but with 48 stars and 1.0% credibility, it's alpha software best for causal ML tinkerers. Strong docs and synthetic benchmarks help, but wait for v0.5 pretrained causal transformers if you need production weights. Solid foundation for custom marketing sims.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.