Conversation Memory No native equivalent

index_conversations

Index Claude Code conversation history. Auto-discovery at startup, session-end hook for re-indexing. Noise filtering built in.

What it does

Indexes Claude Code conversation history for the current project. Runs automatically at startup via auto-discovery. Includes a session-end hook for immediate re-indexing.

Noise filtering

  • tool_result dumps stripped
  • tool_use blocks truncated
  • Images replaced with [image]
  • Compaction-aware: skips summary injections, indexes last summary as meta-document

Related tools

search_conversations search_all_conversations find_conversations_for_symbol

Benchmark note

This benchmark compares CodeSift against the closest practical native workflow an agent would use for the same task. For some tools, that baseline is a direct shell equivalent such as rg or find. For AST-aware, graph-aware, and LSP-backed tools, the baseline is a multi-step workflow rather than a strictly identical command. Results should be read as agent-workflow comparisons: token cost, call count, and practical context efficiency.