Popular repositories Loading

1. driftbench driftbench Public

   Deterministic benchmark for belief-drift & conflict tracking in cognitive systems — part of ongoing work on evaluation reliability for memory/agent systems.

   Python

2. ci-shell ci-shell Public

   Instantly attach to the container of a failed gitlab-ci-local job

   TypeScript

3. mem-audit mem-audit Public

   External, read-only consistency auditor for Mem0-based memory stores — finds duplicate, contradictory, and stale facts without modifying your data

   Python

4. tbg-postmortem tbg-postmortem Public

   A negative-result study and a falsification protocol for LLM memory systems.

   Python

5. evaleval-audit evaleval-audit Public

   Python