Modules§
- adaptive
- adaptive_
thresholds - agents
- attention_
model - Heuristic attention prediction model for LLM context optimization.
- benchmark
- buddy
- cache
- codebook
- compressor
- config
- deps
- entropy
- error
- feedback
- filters
- gotcha_
tracker - graph_
index - intent_
engine - knowledge
- litm
- mode_
predictor - neural
- Neural context compression — trained models replacing heuristic filters.
- patterns
- preservation
- protocol
- quality
- semantic_
cache - semantic_
chunks - Semantic Chunking with Attention Bridges.
- session
- signatures
- signatures_
ts - slow_
log - stats
- surprise
- Predictive Surprise Scoring — conditional entropy relative to LLM knowledge.
- symbol_
map - task_
briefing - task_
relevance - theme
- tokens
- updater
- vector_
index - version_
check - wrapped