← axon dendrite

open source · reliability stack

axon labs

tools for when an llm has to be right enough to ship. detection, observability, context, chunking — no theater.

6 systems python-first built to be used
01
catch-cap

hallucination detection. four methods — semantic entropy, log probs, web grounding, llm-as-judge. one api call. a confidence score you can actually ship on.

02
detra

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

03
contextf

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

04
chunk-it-pro

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

05
secretstuff

pii detection and redaction via gliner. 150+ entity types. reversible — store mappings, restore originals from redacted text.

06
tab

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