Marble Case Manager vs Ojuri
Marble Case Manager
checkmarble.comOjuri
ojuri.ioSide by side
| Figure | Marble Case Manager | Ojuri |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | Yes |
| Web | Yes | Yes |
| Windows | — | Yes |
| Linux | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 3 | 2 |
| Spec score · Financial Fraud Detection Software | 8.0 (#4) | 8.4 (#2) |
| Audit trail | Case activity, decisions, and workflow changes are tracked, versioned, and timestamped. | Ojuri records each decision and the feature snapshot used at inference before returning the response. |
| Deployment | The investigation page describes SaaS or on-premise deployment, including multi-tenant self-hosted and multi-instance options. | The quickstart uses Docker Compose and requires Docker and Node 20; the investigation model is optional and downloads about 7.6 GB of weights when enabled. |
| Integrations | Marble says its open data model can unify data from core banking and third-party tools, and its REST API can create and update objects. | The stack uses Kafka, Redis, PostgreSQL, ONNX Runtime, Docker Compose, NGINX, and Prometheus/Grafana components. |
| Purpose | Marble Case Manager replaces fragmented tools, spreadsheets, and manual processes with an AI-powered case management product for fraud and AML investigations. | Ojuri is a self-hosted fraud detection engine that scores transactions and returns accept, review, or decline decisions. |
Plans
Marble Case Manager
- FreeFree
- StartPriced on request
- EnterprisePriced on request
In their own words
Marble Case Manager
Marble Case Manager has no write-up on Specifiction yet; its figures are above.
Ojuri
Ojuri is a self-hosted fraud detection engine for fintechs, payment gateways, and mobile-money platforms. It scores transactions and returns accept, review, or decline decisions, with applications able to call its POST /v1/predict API. The Real-Time Detection Agent scores payments on the authorization path using an XGBoost model served through ONNX Runtime. A Pattern Analysis Agent follows account, device, and payee relationships over time to identify fraud rings and mule networks. Decisions record reason codes and the data considered by the model in an audit log. Sentinel provides a review queue, decision stream, model registry, and analyst overrides that can become training data. Other agents monitor drift, retrain on verified labels, and check evaluations before model promotion. An optional investigation agent creates reports for declined transactions using a self-hosted language model, separate from live scoring. Ojuri says its services and transaction data remain within the operator’s infrastructure. The project is MIT licensed, with no per-call fees or rate limits.