Skip to main content
Monomento indexes markdown documents into SQLite, enabling fuzzy search by topic and reference graph navigation. It stores full document content — no filesystem access needed after indexing.

​
Quick Start

# Index a documentation directory
monomento index ~/docs

# Search by topic
monomento search "trigram search"

# Follow reference graph
monomento tree SKILL.md --depth 2

# Read document structure
monomento peek LLM-BEHAVIORAL-PATTERNS.md

# Read full content from DB
monomento read 08-smpc-defined.md

​
Memory Access Flow

┌──────────────────────────────────────────────────────────────────┐
│  MEMORY ACCESS FLOW                                              │
├──────────────────────────────────────────────────────────────────┤
│                                                                  │
│  1. SEARCH  →  Find documents by topic (fuzzy trigram)           │
│  2. TREE    →  Follow reference graph, narrow the path           │
│  3. PEEK    →  Read document structure + content previews        │
│  4. READ    →  Retrieve full content from DB                     │
│                                                                  │
│  Each result guides your next move.                              │
│                                                                  │
└──────────────────────────────────────────────────────────────────┘

​
Commands

Find documents matching a topic using trigram fuzzy matching. 
monomento search <query> [-n limit] [--read] [--h2] [--h2+] [--explain]
FlagDescription
-n <limit>Max results (default: 20)
--readShow full section content inline
--h2Filter sections by exact heading level
--h2+Filter by level range (h2 and deeper)
--explainShow score component breakdown

​
tree / chain

Follow reference graphs (DFS tree or BFS chain). 
monomento tree <document> [--forward|--backward] [--depth N]
monomento chain <document> [--forward|--backward] [--depth N]

​
peek

Read full document structure with content previews. 
monomento peek <document>

​
read

Retrieve full content from database (no filesystem needed). 
monomento read <document> ["Section Name"] [--h2] [--h2+]
monomento read <doc1> <doc2> --h2             # Multi-doc read
monomento read <doc1> <doc2> --h2 "filter"    # Multi-doc + name filter

​
bridge

Find content-similar documents (Jaccard similarity on trigrams). 
monomento bridge <document> [-n limit] [--cross]
monomento bridge <doc1> <doc2>                 # Pairwise comparison

​
deps / rdeps

monomento deps <document>     # What does this document reference?
monomento rdeps <document>    # Who references this document?

​
index / stats

monomento index <path> [--ext md,mdx,aiin] [--project]
monomento stats [--project]

​
Document Types

ExtensionDescription
.mdMarkdown documents
.mdxMDX documents (Markdown + JSX)
.aiinAIIN fragments (consciousness anchors)
.txtPlain text documents
All types are parsed for headings, links, mentions, anchors, and trigram content.