AI·rete·RAG
a Rete rule engine decides, RAG explains why
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lending, fraud, clinical triage), then bolt on "guardrails" after the fact.It runs the two in series instead:1. A pure-Python Rete engine evaluates YAML rules against your facts. The verdict comes only from here. Same facts, same verdict, every time, with salience-based conflict resolution. 2. RAG retrieves passages from your own policy documents, and an LLM writes a plain-English explanation of the decision that was already made, citing those passages. It can't change the verdict.A few things that went further than I expected: - Rules are a graph, not flat lists: nested all/any/not, and rules can assert facts that other rules consume (forward chaining). The decision trace shows the causal chain. - Audit mode records every rule evaluated, including the ones that didn't fire, condition by condition, with a snapshot of the rule set for replay. - Rules can steer retrieval (a fired rule narrows which documents get searched), and retrieved text can be turned into facts for the engine. - Non-technical authors can build rules in a visual editor, or paste a policy document and get LLM-drafted rules with citations. Drafts are never saved without review. YAML is still there for engineers.The landing page has a live demo with no signup (8 demo domains: loan, fraud, clinical, insurance, legal, ops, e-commerce, blockchain). There's also an MCP server, so Claude and other agents can call /decide as a tool: `uvx ai-rete-rag-mcp`.To be upfront: it's a hosted product with a free tier. The MCP client is open source (MIT, github.com/zaharajabeen13-create/ai-rete-rag-mcp); the engine and platform are not open source right now.I'd especially like to hear from anyone who has had to explain an automated decision to a regulator or an auditor: what did they actually ask for?
HN · launched Sep 22, 2026 · 44 upvotes (top 16%) · 0 views
Niche: rag developer frameworks and tools · 59 launches, 2 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Agent / copilot
- Developer
- AI-native
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 59 launches in rag developer frameworks and tools →
Could you build this?
Yes The product connects an open-source Python Rete algorithm implementation (like experta or pyknow) with an LLM prompt pipeline to explain matched deterministic rules.
Discussion
2 comments analyzed.
Competitors mentioned: Drools
Concerns raised: Using LLMs to explain rules instead of displaying passed/failed logic
Competitors
Other products that read as similar to this one : 152 launches clear the similarity bar, closest 8 shown.
Attention rank: #21 of 153 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 323 days after the earliest competitor.
- I built a RAG engine to search Singaporean laws · hn · 2026-02-07 · 5 upvotes · similarity 0.46
- LLMValidate.ai · ph · 2026-10-22 · 2 upvotes · similarity 0.43
- Ragnerock, an AI data analysis tool · hn · 2026-04-28 · 13 upvotes · similarity 0.43
- Askfeather.ai · hn · 2026-02-03 · 7 upvotes · similarity 0.43
- Replacing $50k manual forensic audits with a deterministic .py engine · hn · 2026-03-14 · 5 upvotes · similarity 0.42
- LLMs each trading $100K vs. a frozen rulebook · hn · 2026-08-17 · 12 upvotes · similarity 0.42
- I automated forensic accounting for divorce cases (3 min vs. 4 weeks) · hn · 2025-12-22 · 6 upvotes · similarity 0.41
- Was tired of drowning in HN comments, so I built an AI Chief of Staff · hn · 2026-01-26 · 5 upvotes · similarity 0.40
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.