Skip to content
View obversary's full-sized avatar
🎯
BUILDING
🎯
BUILDING

Organizations

@obversarystudios

Block or report obversary

Report abuse

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

Report abuse

Pinned Loading

  1. memory-layer-substrate memory-layer-substrate Public

    memory substrate

    Python

  2. failure-induced-benchmarks failure-induced-benchmarks Public

    This repo studies whether benchmarks can be generated from model failure geometry.

    Python

  3. earth-database earth-database Public

    A local embedded memory system with SQLite/WAL, FTS5 retrieval, JSONL observability, explicit provenance, scheduler jobs, and now a trust-aware ingestion layer.

    Python

  4. obversary-eval-harness obversary-eval-harness Public

    Lightweight Python evaluation harness for testing systems against reproducible benchmark tasks.

    Python

  5. obversarystudios/TSPbenchmark obversarystudios/TSPbenchmark Public

    AHA submission | TSP measures whether an assistant helps the user continue the real work, not merely answer the visible question.