Skip to content

ctxrot

Alpha

ctxrot currently supports only DSPy>=3.1.3 and may produce mis-aligned output. Please report any issues you encounter — the API may change.

Install

uv add ctxrot

What it does

  • Records every LM call and tool call from your DSPy agent into a local SQLite database via a drop-in CtxRotCallback.
  • Detects repetition and efficiency degradation — the two signals of context rot — without making any LLM calls of its own.
  • Visualizes sessions in a Textual TUI dashboard with growth curves, per-iteration metrics, and an RLM tree view.
  • Exports sessions to JSONL in the opentraces TraceRecord shape (or a native format), ready to share or archive.
  • Deep-analyzes a session with an RLM agent that produces a structured rot report — optional, requires Deno + an API key.

Next steps

  •   Quickstart — attach the callback, run your agent, open the dashboard.
  •   Concepts — what context rot is and the metrics ctxrot uses to detect it.
  •   CLI reference — dashboard, analyze, export, deep-analyze, reset.
  •   Python API — CtxRotCallback, CtxRotStore, analyze_session, run_deep_analysis.