Pinned Loading

1. context-engine context-engine Public

   A pure-Python context management layer for LLM systems — retrieval, re-ranking, memory decay, and token-budget enforcement in one pipeline.

   Python 185 27

2. temporal-rag temporal-rag Public

   A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one pipeline.

   Python 23 2

3. hallucination-detector hallucination-detector Public

   Production RAG hallucination detection + self-healing pipeline — 5 checks, 3 healing strategies, zero external APIs

   Python 10 4

4. react-retry-waste-analysis react-retry-waste-analysis Public

   ReAct agents waste 92.6% of retries. Here's the architecture fix (error taxonomy + circuit breakers + deterministic routing) that drops waste to 0%.

   Python 7