Skip to content

Observability

Terminal window
graymatter tui

Opens a live terminal dashboard with everything your agent memory is doing — no extra setup required. Auto-refreshes every 5 seconds. Press 1–4 to switch tabs, r to force refresh, q to quit.

What you get at a glance:

  • Facts — total stored, distributed across agents
  • Memory cost — KB on disk (text + embeddings), not tokens
  • Recalls — cumulative access count across all sessions
  • Health — percentage of facts above relevance threshold (weight > 0.5)
  • Token cost (30d) — real spend breakdown by model, with cache hit rate
  • Agent activity — facts vs recalls per agent, side by side
  • Weight distribution — how consolidated your memory is over time
  • Activity timeline — facts created per day, last 30 days

If another process holds the write lock, open the TUI in read-only mode explicitly: graymatter tui --read-only.

Terminal window
graymatter doctor --audit [path]

Measures tokens, duplicates, staleness, and marker conflicts in any instruction file (CLAUDE.md, AGENTS.md, …). Free auditor, no LLM required.

Terminal window
graymatter doctor --graph

Hubs by degree, articulation points, orphans, and a declared connectivity ratio for the knowledge graph.

Terminal window
graymatter status # facts, recalls, KG state, injection estimate
graymatter bench # audit the published benchmark figures from the binary

Every figure on the benchmarks page is machine-checked against a live run in CI.