Create a durable markdown memory for facts, decisions, preferences, or project context that should survive beyond the current chat.

Retrieve a memory note by id and return its complete markdown with YAML frontmatter.

Append new markdown to an existing memory while preserving its current content and updating the modified timestamp.

Patch memory metadata and optionally replace the full markdown body. Use append_memory when adding incremental observations.

Mark a memory as archived without deleting its markdown file.

Permanently delete a memory note by id.

List memory metadata for browsing or filtering without returning full note bodies. Use search_memory when you need relevance ranking.

Search durable memories with relevance ranking over title, aliases, tags, path, description, and body terms.

Record an append-only memory trace for shared agent experience. Traces are raw observations that agents can later consolidate into durable memories.

Agent-friendly write API that records a trace and deterministically chooses whether to create a new memory or append to a strongly matching existing memory.

Return a compact, deterministic recall bundle for an agent task using lexical match, metadata, salience, access history, status, and optional wikilink traversal.

Mark a memory as accessed, updating last_accessed_at, access_count, and salience.

Suggest groups of raw traces that may deserve consolidation. Smriti does not summarize them; the agent decides the final memory content.

Create, append, or update a durable memory from agent-supplied consolidated content. Use after reviewing traces; Smriti records provenance but does not summarize content itself.

Mark one memory as superseded by another while preserving both markdown files.

Review memory store health by reporting duplicate titles, stale active memories, oversized notes, and unresolved wikilinks without modifying files.

Build or refresh the human-readable markdown memory index at index.md.

Repair and rebuild the memory store: optionally fix frontmatter, apply or normalize wikilinks from memory titles and aliases using longest matches first, then rebuild index.md and index.yaml.

Load the generated markdown memory index, optionally refreshing it first.