AI·rete·RAG: Rule Engine Decides, RAG Explains Why

AI·rete·RAG separates auditable decisions from LLM explanations: a pure-Python Rete engine evaluates YAML rules against facts to produce a single verdict, while RAG retrieves policy passages so an LLM writes a cited explanation without changing the verdict. It offers a free tier and an MCP server for agents like Claude.

• User Says Anthropic Wrongly Tagged Them for Training Competitor Model2026-10-31
• Anthropic study: harmless-looking data can train models to sabotage oversight2026-10-31
• Anthropic model finds Linux kernel bug enabling remote root access2026-10-30
• HN users question sudden Opus 5.5 quality drop2026-10-30
• Study uses Claude-enabled antibody design for food allergy IgE disruptor2026-10-29