Vishap

🔬 6-stage LLM pipeline for analyzing engineering materials (code, spec, logs).

Vishap takes a file as input → returns a structured Markdown report with risks, STRIDE threat model, refactoring options and audit trail with PII detection and compliance flags.

🌐 Links

• Documentation: https://dvddv9.github.io/vishap/
• Landing Page: https://dvddv9.github.io/vishap/landing/
• GitHub App: Auto-analyze PR diffs and comment on findings.

🚀 What's new in v6.1.0 (SaaS Release)

We have transformed Vishap from a local tool into a full-fledged SaaS platform:

• Queue (Celery + Redis): Production-ready async processing (/analyze/async).
• GitHub App: Webhooks + PR auto-analyze with inline comments.
• Auth (Clerk): Multi-tenant JWT authentication (/analyze/secure).
• Billing (Stripe): Subscriptions + usage-based billing (Checkout API).
• Docs (Docusaurus): Full documentation site on GitHub Pages.
• Landing (HTML/Tailwind): Static marketing page.
• Observability (OTel): Distributed tracing (Tempo) + metrics (Prometheus) + Grafana dashboards.
• PostgreSQL: JobStore abstraction for persistent job tracking.

🛠 Features

• 6-stage pipeline: Ingestion → Taint Analysis → Dataflow → Risk Assessment → Verdict → Report.
• Multi-language: Python, Java, C (AST + taint patterns).
• Async API: FastAPI with Celery workers.
• Security: Fernet encryption for secrets, HMAC for webhooks.
• Observability: Structlog (JSON), Prometheus /metrics, OpenTelemetry traces.
• CI/CD: GitHub Actions (tests, lint, docs deploy, dogfood).

📦 Quick Start

Docker (recommended)

git clone https://github.com/dvddv9/vishap.git cd vishap cp .env.example .env docker compose up -d

• UI: http://localhost:8501
• API: http://localhost:5001/docs
• Grafana: http://localhost:3001

🧪 Testing

python -m pytest tests/ --ignore=tests/test_e2e.py -q

553 passed

📄 License

MIT License. See LICENSE for details.