## https://sploitus.com/exploit?id=F8CCEDFC-8DCA-574C-967E-8E39955A9CD2
ο»Ώ# Project Ronin Documentation Hub
Welcome to the technical documentation repository for **Project Ronin** β an autonomous, AI-powered black-box API security testing platform designed for 100% local execution.
This documentation suite is organized according to standard enterprise engineering practices, covering architectural blueprints, schema specifications, developer guides, design decision records (ADRs), testing strategies, and threat models.
---
## π Documentation Index
```
docs/
βββ architecture/ # High-level system & agent design
β βββ system-architecture.md
β βββ agent-architecture.md
β βββ data-flow.md
βββ api/ # Input, output, and internal state contracts
β βββ input-schema.md
β βββ output-schema.md
β βββ state-schema.md
βββ guides/ # Developer onboarding & workflows
β βββ setup-guide.md
β βββ contributing.md
βββ design/ # Architectural Decision Records (ADR)
β βββ adr/
β βββ 001-local-llm-only.md
β βββ 002-cli-first.md
βββ testing/ # QA & verification strategies
β βββ test-plan.md
βββ security/ # Threat modeling & safety controls
β βββ threat-model.md
βββ project-plan/ # Roadmaps & sprint schedules
βββ timeline.md
βββ milestones.md
```
---
## ποΈ 1. Architecture
Comprehensive system blueprints detailing how Project Ronin orchestrates autonomous penetration testing.
* **[System Architecture](architecture/system-architecture.md)**
High-level overview of the Docker Compose topology, service interconnects, FastAPI orchestrator, local Ollama engine, MongoDB persistence, and the Alpine Linux sandbox.
* **[Multi-Agent Architecture](architecture/agent-architecture.md)**
In-depth breakdown of the 4-agent LangGraph state machine: Orchestrator, Reconnaissance Agent, Exploitation Agent, and Validation Agent.
* **[Data Flow Documentation](architecture/data-flow.md)**
End-to-end data lifecycle sequence diagrams mapping request transformation from user CLI input to final JSON/HTML vulnerability reports.
---
## π 2. API & Data Contracts
Exact data structures, CLI interfaces, and runtime state definitions.
* **[Input Schema Specification](api/input-schema.md)**
CLI argument reference for `ronin scan`, covering Base URL auto-discovery, Postman Collection ingestion, plain text endpoint lists, and `--include`/`--exclude` scope filtering.
* **[Output Schema Specification](api/output-schema.md)**
Schema definitions for machine-readable JSON reports, standalone executive HTML reports, and interactive terminal progress indicators.
* **[Global State Schema](api/state-schema.md)**
Pydantic v2 data models for `ScanState`, `Endpoint`, `Parameter`, `SuspectedVuln`, and `Finding`, including agent read/write permissions.
---
## π οΈ 3. Guides & Developer Onboarding
Step-by-step instructions for running, extending, and contributing to the codebase.
* **[Development Setup Guide](guides/setup-guide.md)**
Local environment prerequisites, Docker Compose provisioning, Ollama `qwen2.5-coder:7b` setup, and troubleshooting common issues.
* **[Contributing Guidelines](guides/contributing.md)**
Code standards, Conventional Commits format, PR workflows, and walkthroughs for adding new agent tools and custom vulnerability checks.
---
## βοΈ 4. Architecture Decision Records (ADRs)
Key architectural decisions, trade-offs, and rationale documented in standard ADR format.
* **[ADR-001: Local LLM Only](design/adr/001-local-llm-only.md)**
Rationale for standardizing strictly on local Ollama + Qwen 2.5 Coder 7B for total data privacy and zero ongoing API costs.
* **[ADR-002: CLI-First Architecture](design/adr/002-cli-first.md)**
Rationale for launching V1 as a modular CLI tool powered by Typer and Rich before developing the Next.js web dashboard.
---
## π‘οΈ 5. Security & Threat Modeling
Safety boundaries, sandboxing guarantees, and defense mechanisms.
* **[Threat Model & Security Considerations](security/threat-model.md)**
STRIDE analysis of the testing engine, Docker sandbox isolation and escape prevention, scope locking, indirect prompt injection mitigations, and air-gapped data privacy assurances.
---
## π§ͺ 6. Testing & Quality Assurance
Verification methodologies and benchmark targets.
* **[Testing Strategy & Plan](testing/test-plan.md)**
Unit testing, agent integration testing with mock APIs, and end-to-end validation against deliberately vulnerable targets like OWASP crAPI and vAPI.
---
## π
7. Project Planning & Roadmaps
Execution schedules and future capability roadmaps.
* **[Development Timeline & Sprint Plan](project-plan/timeline.md)**
Detailed 6-day sprint schedule with daily task breakdowns, acceptance criteria, and risk mitigation strategies.
* **[Project Milestones](project-plan/milestones.md)**
Evolution roadmap tracking V1 (6-day CLI MVP), V2 (Authenticated scans & Web UI), and V3 (DevSecOps CI/CD & fine-tuned models).