Ojuri vs Tazama
Ojuri
ojuri.ioTazama
tazama.orgSide by side
| Figure | Ojuri | Tazama |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | Yes | Yes |
| Web | Yes | Yes |
| Windows | Yes | Yes |
| macOS | — | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 2 | 1 |
| Spec score · Financial Fraud Detection Software | 8.4 (#2) | 8.3 (#3) |
| Spec score · Payment Fraud Detection Software | 8.5 (#6) | 8.3 (#8) |
| Deployment | 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. | A Docker Compose stack runs the platform on one machine for evaluation, and production deployment guides cover Kubernetes on premises, EKS, GKE and AKS. |
| Integrations | The stack uses Kafka, Redis, PostgreSQL, ONNX Runtime, Docker Compose, NGINX, and Prometheus/Grafana components. | The platform connects to REST APIs, message queues, external case systems and real-time alert routes. |
| License | The repository is released under the MIT license. | Tazama repositories identify the Apache License 2.0. |
| Purpose | Ojuri is a self-hosted fraud detection engine that scores transactions and returns accept, review, or decline decisions. | Tazama is an open-source, real-time transaction-monitoring platform for detecting fraud and associated money-laundering typologies. |
| Security controls | The documentation describes API keys, dashboard accounts and roles, signed webhooks, and idempotency keys for safe retries. | Official product material cites Keycloak authentication, tenant controls, logging, role-based workflows and auditability. |
| Self-hosting | Ojuri runs on the operator’s servers with Docker Compose and does not require a SaaS account. | The project provides Docker Compose stacks for local or multi-server deployment and Kubernetes-oriented cloud infrastructure. |
| What it does | Ojuri scores payment transactions before authorization and returns accept, review, or decline decisions with reasons. | Tazama is an open-source platform for real-time transaction monitoring, fraud detection and money-laundering typologies. |
Plans
In their own words
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.
Tazama
Tazama is an open-source platform for monitoring transactions in real time for fraud and money-laundering typologies. It evaluates current transaction information together with historical participant behavior, applies configurable rules and thresholds, and can block high-risk payments or send alerts for investigation. Rule Studio gives analysts visual rule building, transaction replay, and review before deployment. Connection Studio and DEMS map and ingest message formats, including ISO 20022 payment messages. Investigators manage alerts through triage, assignment, investigation, filing, and closure in a case system that records decisions. BIAR combines detection and case results in a lakehouse with dashboards and calibration notebooks. Studio changes, case actions, triage decisions, and workflow transitions are audited. Docker Compose supports evaluation on one machine; production guides cover on-premises Kubernetes, EKS, GKE, and AKS. The software has no license charge, but hosting, implementation, and support require resources.