staleness

The lockers package contains various locking mechanism and building blocks.

Temporal-awareness hook for tool-using LLMs — surfaces freshness verdicts on in-context data so stale information doesn't poison fresh reasoning. Adapters for Claude Code, Antigravity, and any generic harness.

QA traceability & LLM test-case generation: versioned doc tree -> LLM test-case drafts -> staleness detection that catches when a test case still looks valid but no longer matches a changed requirement.

Telemetry-based auditor for measuring dynamic memory quality in LLM agents using the MemoryFlow framework.

W3C PROV knowledge graph on plain Postgres with automatic staleness propagation — a verified-facts bank for AI agents (proof of concept)

When the network is removed, which failures are silent -- and how often the status artifact an accreditation review receives cannot tell a healthy enclave from one months past its budgets.

Make a derived artifact refuse to pretend it is fresh.

Says whether a signal is fresh, stale, or dead, from its real timestamp

Tell whether your data is fresh, not merely rewritten. Four independent freshness layers -- the signal is the divergence between them.

Fact-level staleness detection for AI agent memory