Real-time spend tracking, cost prediction, and runaway-loop circuit breakers for LLM API calls. Zero dependencies.
DOM AST pruning for LLM pipelines — 90%+ token reduction, no API key
A self-hostable memory engine for AI agents that can distinguish what was true from what the agent knew at the time - g-33-L/anansi
Knowledge-graph-augmented retrieval for RAG systems: Neo4j-backed entity extraction (regex or LLM-based), co-occurrence graphs, entity deduplication, and GraphRetriever for hybrid vector+graph retrieval via the optional ragleap-rag integration. Framework-agno…
Dynamo Inference Framework Runtime
