Skip to main content
PuzldAI includes a memory system that stores conversations, decisions, and code patterns for future retrieval.
For codebase indexing and search, see Indexing & Search.

​
Memory Types

TypeDescription
conversationQ&A pairs from sessions
decisionAccepted file edits and explanations
codeCode snippets and patterns
patternReusable solutions

​
How It Works

  1. Automatic storage — When you accept file edits, the decision is stored
  2. Semantic search — Prompts are matched against stored memories
  3. Context injection — Relevant memories are injected into agent prompts

​
Storage

All memory data is stored in the main database: 
~/.puzldai/
├── puzldai.db       # SQLite database (memories, sessions, observations)
└── sessions/        # Legacy JSON session files

​
Embedding Models

When Ollama is available, PuzldAI uses embeddings for semantic search:
ModelNotes
nomic-embed-textRecommended
mxbai-embed-largeAlternative
all-minilmLightweight
If no embedding model is available, FTS5 full-text search is used.

​
Sessions

Chat history is persisted between sessions: 
# TUI
/session                  # Start new session
/resume                   # Resume previous session

# CLI
puzldai session list      # List sessions
puzldai session new       # Create new session