dive-memory-v3

name	dive-memory-v3
description	Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.

Dive-Memory v3: MCP-Based Persistent Memory System

Dive-Memory v3 provides long-term persistent memory for AI agents, solving the "context forgetting" problem across sessions.

Core Capabilities

1. Memory Storage

Store memories with rich metadata using the Python API:

from dive_memory_v3 import DiveMemory

memory = DiveMemory()

# Add memory
memory.add(
    content="Fixed JWT auth bug with refresh token rotation",
    section="solutions",
    subsection="authentication",
    tags=["jwt", "security", "bug-fix"],
    importance=8,
    metadata={"code_snippet": "...", "success_rate": 1.0}
)

2. Semantic Search

Search using natural language + hybrid search (vector + keyword):

# Search memories
results = memory.search(
    query="How to fix JWT authentication issues?",
    section="solutions",
    tags=["authentication"],
    top_k=
)

 result  results:
    ()
    ()