AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Insurance › aml-fraud-transaction-monitoring
✦ Free & open sourceInsurance

aml-fraud-transaction-monitoring

Real-time AML and fraud detection platform powered by agentic AI and hybrid machine learning models.

Open-source agentic transaction monitoring and AML framework

Detect fraud and money laundering in real time using rules, ML models, and interactive AI agents.

Free forever · open source · AGPL-3.0
✓ Needs IT✓ Browser-based✓ Real-time collaboration
6.6
ZEKAI
Powerful self-hosted AML engine.
Free & open source · Insurance
Ease of setup4
Usefulness8
Maintenance9.5
Community5
★ 115
GITHUB
Oct 2026
UPDATED
AGPL-3.0
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

Jube is a real-time anti-money laundering (AML) and transaction monitoring engine designed to flag suspicious financial activity. It pairs traditional rule-based logic and machine learning with an agentic AI assistant for compliance investigations. You should use it if you need an auditable, self-hosted transaction screening platform.

Runs on
Web
Hosting
Self-host
Languages
C#
License
AGPL-3.0

What it is

The platform screens incoming transactions using velocity checks, sanctions screening, rule engines, and supervised or unsupervised machine learning. Its natural-language assistant, Jooby, coordinates specialized AI agents to execute platform actions and provide explainable steps for auditors. It also includes native case management features so compliance officers can manage alerts directly.

Who it's for

This tool suits insurance carriers, fintech developers, and compliance engineers who need self-hosted transaction monitoring without vendor lock-in. It does not suit non-technical teams looking for a fully managed SaaS service that requires no infrastructure administration.

Key features

Hybrid Machine Learning Detection

Combines configurable business rules, velocity limits, and sanctions screening with supervised and unsupervised machine learning.

Agentic AI Query Interface

Coordinates over 150 specialized AI agents to answer natural-language questions and present step-by-step decision trails.

Built-In Case Management

Provides built-in workflow tools for compliance officers to investigate, document, and manage flagged transactions.

High-Availability Swarm Architecture

Scales across multi-node clusters using PostgreSQL under Patroni, Redis under Sentinel, and HAProxy load balancing.

How to start

Up and running in 3 steps

1
Clone the repository and replace the default key environment variables with strong custom secrets in your terminal.
2
Start the single-node evaluation stack by running docker compose up -d.
3
Log into localhost:5001 using Administrator credentials, change the password, and optionally add an inference key to enable Ask Jooby.
Real talk

Our honest verdict

What's great

  • Combines rule engines with explainable supervised and unsupervised machine learning models.
  • Generates step-by-step audit trails suitable for regulatory reviews during investigations.
  • Includes built-in case management so teams do not need separate alert-handling software.
  • Runs entirely on your own infrastructure with zero mandatory third-party data sharing.

Where it falls short

  • Requires substantial IT skill to configure high-availability cluster components like Patroni and Redis Sentinel for production.
  • Using the natural-language agent interface requires paying for external OpenAI-compatible API inference services.
  • The initial Docker Compose setup requires manually defining multiple security keys and passwords in environment variables.
Cost

Pricing & license

The software is free to run under the AGPL-3.0 licence. Your only expenses are the infrastructure compute resources and any third-party API fees incurred if you enable LLM features.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: aml-fraud-transaction-monitoring for Insurance
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure aml-fraud-transaction-monitoring for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I run this platform without enabling the AI agent features?

Yes. You can leave the Ask Jooby flag set to False and use the rule engine, machine learning models, and case management tools without an LLM.

Which AI models or API providers does Ask Jooby support?

It uses DigitalOcean Serverless Inference by default, but you can point it to any OpenAI-compatible API endpoint.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Insurance — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google