Skip to content
View Emmimal's full-sized avatar
🤩
Focusing
🤩
Focusing

Block or report Emmimal

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

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 196 30

  2. wiki-compiler wiki-compiler Public

    A pure-Python compiler that turns raw markdown notes into a linked, linted wiki. Zero dependencies, zero LLM calls, fully deterministic.

    Python 88 11

  3. control-layer control-layer Public

    A production-grade control layer that sits between your application logic and any LLM — input validation, schema enforcement, circuit breaking, targeted retry, and audit logging in one composable p…

    Python 62 8

  4. 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 49 8

  5. context-graph-benchmark context-graph-benchmark Public

    A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.

    Python 30 5

  6. context-compiler context-compiler Public

    A pure-Python reachability and skeletonization layer that decides what a coding agent actually sees before a request reaches the API.

    Python 60 1