HN Showcase
Back to browse
GitHub Repository

⚡ Real-time AI. Cross-verified. Always current. Costs NOTHING.

2 starsPython

Kairos, real-time AI who cross-verifies (Python, 100KB)

by joshuaveliyath·Mar 9, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●●GemZero to OneWizardryBig Brain

Cross-verifies across multiple sources before the LLM sees context — stops hallucinations at the source.

Strengths
  • •Confidence scoring based on independent source agreement — 4+ sources = HIGHLY VERIFIED.
  • •100KB Python script with dynamic thinking budget — 0 tokens for facts, up to 10k for analysis.
Weaknesses
  • •Requires self-hosting and API keys for NewsAPI — not quite zero-cost despite the claim.
  • •Only 6 commits and 0 stars — very early stage, needs real-world stress testing.
Category
AI/ML
Target Audience

Anyone frustrated by AI hallucinating on current events or live data

Similar To

Perplexity · ChatGPT with Browse · Gemini

Post Description

Hi HN, I'm Joshua, a teen from Kerala, India.

I built Kairos because I was frustrated that every AI I tested hallucinated on live events. During today's T20 World Cup Final, ChatGPT named the wrong player. Copilot named a different wrong player. Both confidently. Neither had live data.

Kairos solves this differently. Instead of sending raw search results to the LLM and hoping, it runs a verification pass first — cross-checking titles across RSS, DuckDuckGo, and NewsAPI, scoring each result by how many independent sources confirm it, then sorting by confidence before the LLM ever sees the context.

The architecture:

1. Pronoun resolution from ChromaDB conversation history (no API call) 2. Domain classification (6 domains) 3. Query expansion — 1 query becomes 4 targeted searches, pure Python, zero extra API calls 4. Parallel async fetch with timeouts 5. Cross-verification scoring 6. Dynamic thinking budget (0 for sports scores, up to 10k for complex analysis, hard capped) 7. 250 word output limit

Total codebase: ~90KB Model: Gemini 2.5 Flash Cache: ChromaDB Cost: $0

Benchmark on today's T20 Final: Kairos 43/50, Gemini 40/50, Perplexity 38/50, Copilot 26/50, ChatGPT 19/50

ChatGPT and Copilot both hallucinated player names with full confidence. Kairos cited 15 live sources.

GitHub: https://github.com/joshuaveliyath/kairos

Happy to answer technical questions.

Similar Projects