v4.1.0 — Review Console & Architecture Diagram

What's New in v4.1.0

Added

• Review Console: Minimal human-in-the-loop review console for HITL workflows and remediation tracking. Allows reviewers to approve, reject, comment on, and track remediation status of security findings.
• Architecture Diagram: Embedded system architecture diagram across all READMEs, ARCHITECTURE.md, and project documentation for clearer visual overview of the platform.

Changed

• Documentation: Redesigned architecture diagram for improved clarity; updated all language-specific READMEs (en, zh, ja, ko, fr, de) to include the diagram.

---

Test Results

All 34 tests passed ✓

See CHANGELOG.md for full history.

v2.0.0

docs(changelog): update for v2.0.0 release

v0.3.0

See CHANGELOG.md for full details.

v0.2.0

[0.2.0] — 2026-03-06

Added

• Streamlit Frontend: A modern, interactive dashboard for managing assessments and knowledge base.
  • Dashboard: Visual metrics and activity charts.
  • Assessment Workbench: Drag-and-drop file upload, real-time progress tracking, and structured report viewing (Risks, Compliance, Remediations).
  • Knowledge Base Manager: UI for uploading policy documents and testing RAG retrieval.
• Developer Experience:
  • Added pyproject.toml for unified tool configuration.
  • Added Makefile for common development tasks (make install, make test, make lint).
  • Added pre-commit hooks for code quality assurance.
  • Integrated Ruff for fast linting and formatting.
• Documentation:
  • Updated README with frontend screenshots and demo GIF.
  • Added DEMO-RECORD.md guide.

Changed

• CI/CD: Updated GitHub Actions workflow to include linting steps.
• Project Structure: Migrated pytest.ini to pyproject.toml.

v0.1.0: First release — Assessment API, RAG, Docker

This is the first official release of Arthor Agent, an AI-powered assistant for security teams: upload documents and questionnaires, compare against your knowledge base and policies, and get structured assessment reports (risks, compliance gaps, remediations).

What's in this release

• Assessment API — Submit PDF, Word, Excel, PPT, or text; get structured reports (risk items, compliance gaps, remediations).
• Knowledge base (RAG) — Upload policy/compliance docs; Chroma chunking & embedding; query endpoint.
• Multi-format parser — PDF, Word, Excel, PPT, plain text/Markdown (PyMuPDF, python-docx, openpyxl, python-pptx).
• LLM abstraction — OpenAI or Ollama (local); set LLM_PROVIDER and env vars.
• REST API — FastAPI: /api/v1/assessments, /api/v1/kb/documents, /api/v1/kb/query, /health; Swagger at /docs.
• Docker — Dockerfile + docker-compose.yml for one-command run (API + Ollama).
• Docs — SPEC, ARCHITECTURE.md, design docs 01–05, SECURITY.md, bilingual README.

Using the ZIP

1. Download Source code (zip) from this release and extract.
2. Docker (recommended):

   cd Arthor-Agent-0.1.0
   docker compose up -d
   # Open http://localhost:8000/docs
   docker compose exec ollama ollama pull llama2