memory-recall

You have three memory tools for progressive recall. Start with search, go deeper only when needed.

Tools (use progressively)

1. memory_search — Start here

Semantic search across all past conversation memories.

• Returns: chunk summaries with dates, topics, chunk_hash identifiers
• Use for: "What did we discuss about X?", "Have I asked about Y before?"

2. memory_get — When search results aren't detailed enough

Expands a specific chunk_hash to show the full markdown section with surrounding context.

• Input: chunk_hash from memory_search results
• Returns: full section text, may include transcript anchors ()
• Use for: "Show me the details", "I need more context on that result"

3. memory_transcript — When you need the exact original conversation

Parses the original session transcript to retrieve the raw dialogue.

• Input: transcript_path from the anchor comment in memory_get results
• Returns: formatted conversation with [Human]/[Assistant] labels and tool calls
• Use for: "What exactly did I say?", "Show me the original conversation"
• If the anchor format is unfamiliar (e.g. rollout:, turn:, db: instead of transcript:), try reading the referenced file directly to explore its structure and locate the relevant conversation by the session or turn identifiers in the anchor.

Decision guide

Tips

• memory_search returns chunk_hash — pass it to memory_get for expansion
• memory_get may reveal <!-- session:UUID transcript:PATH --> anchors — pass the path to memory_transcript
• If memory_search returns no results, try rephrasing with different keywords
• Results are sorted by relevance (hybrid BM25 + vector search)