CAPABILITIES
Text Chunking
Smart segmentation of documents into optimal-sized pieces for embedding
Embedding Storage
Content-hash deduplication with SQLite registry and persistent vector store
HNSW Search
Fast approximate nearest neighbor search powered by USearch
Text Storage
Optional persistent text with LIKE pattern and FTS5 full-text search
Vocabulary
Word-level semantic similarity built from indexed content
CLI Tool
Index, search, and manage everything from the command line
CLI USAGE
Build the tool, then index, search, and explore.
cd my-project
memo index *
memo search "database connection pooling"
[F3] src/db/pool.cr (score: 0.823)
12 | def connect(config : DBConfig)
13 | pool = ConnectionPool.new(config)
[F7] src/db/query.cr (score: 0.781)
45 | # Reuse pooled database connections
46 | conn = pool.checkout
2 result(s)
memo terms "database"
0.70 data
0.70 databases
0.57 sqlite
QUICK START
Add Memo to your Crystal project in minutes.
shard.yml
dependencies:
memo:
github: trans/memo
require "memo"
# Create service with database path
memo = Memo::Service.new(
db_path: "./memo.db",
format: "openai",
api_key: ENV["OPENAI_API_KEY"]
)
# Index a document
memo.index(
source_type: "article",
source_id: 42_i64,
text: "Your document text here..."
)
# Search
results = memo.search(query: "search query", limit: 10)
results.each do |r|
puts "#{r.source_type}:#{r.source_id} (score: #{r.score})"
end
# Clean up
memo.close
SUPPORTED PROVIDERS
Plug in your preferred embedding service.