axon labs

hallucination detection for llms. four methods — semantic entropy, log probabilities, web grounding, llm-as-judge. returns a 0-1 confidence score with automated corrections.

llm observability framework. decorator-based tracing, behavior evaluation via gemini, security scanning, multi-channel alerts. deep datadog integration.

intelligent context builder for documents. pattern-based search with token-aware windowing. 85% token reduction at 99.2% quality retention in evals.

semantic double-pass chunking for rag. finds boundaries by meaning, not character count. lookahead merging keeps related content together.

pii detection and redaction via gliner models. 150+ entity types. reversible — stores mappings to restore originals from redacted text.

wearable ai second brain. raspberry pi zero w + whisper + mistral. records conversations, indexes them, surfaces them when needed. built for adhd support.