This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+5 more
Summary
AI summaryFirst official release of Arthor Agent with assessment API, knowledge base (RAG), multi-format parsing, LLM abstraction, REST API, Docker deployment, and documentation.
Full changelog
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_PROVIDERand env vars. - REST API — FastAPI:
/api/v1/assessments,/api/v1/kb/documents,/api/v1/kb/query,/health; Swagger at/docs. - Docker —
Dockerfile+docker-compose.ymlfor one-command run (API + Ollama). - Docs — SPEC, ARCHITECTURE.md, design docs 01–05, SECURITY.md, bilingual README.
Using the ZIP
- Download Source code (zip) from this release and extract.
- Docker (recommended):
cd Arthor-Agent-0.1.0 docker compose up -d # Open http://localhost:8000/docs docker compose exec ollama ollama pull llama2
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Beta — feedback welcome: [email protected]