Claude Memory Manager

Cross-session memory for Claude Code — never lose context between sessions.

Claude Memory Manager automatically captures architectural decisions, code changes, bug fixes, and configuration choices from your Claude Code sessions, then intelligently retrieves relevant context when you start new sessions.

What It Does

Every time you use Claude Code, valuable context is created and lost when the session ends:

Which libraries you chose and why
Bug fixes and their root causes
Configuration decisions
File structure and naming conventions
Error resolutions

Claude Memory Manager solves this by:

Parsing your Claude Code session logs (JSONL files)
Extracting meaningful memories with importance scoring
Embedding memories for semantic search
Storing everything in a local SQLite database with FTS5
Retrieving relevant context via hybrid semantic + keyword search
Serving context to Claude Desktop via MCP protocol

Installation

pip install claude-memory-manager

For local embeddings (no API key needed): ``bash pip install claude-memory-manager[local] ``

For development: ``bash pip install claude-memory-manager[dev] ``

Quick Start

1. Initialize the Database

claude-memory init

This creates the SQLite database at ~/.claude-memory/memory.db and saves a config file.

2. Ingest Session Logs

# Ingest all sessions from the default path (~/.claude/projects/)
claude-memory ingest

# Ingest from a specific path
claude-memory ingest /path/to/sessions

# Watch for new sessions and auto-ingest
claude-memory ingest --watch

3. Search Memories

# Search across all memories
claude-memory search "authentication setup"

# Filter by project
claude-memory search "database schema" --project /path/to/project

# Filter by category
claude-memory search "cors" --category config

4. Generate Context Summary

# List all indexed projects
claude-memory context

# Generate summary for a specific project
claude-memory context /path/to/project

# With custom token limit
claude-memory context /path/to/project --max-tokens 3000

5. Connect to Claude Desktop (MCP)

Add to your Claude Desktop config (see MCP Setup):

{
  "mcpServers": {
    "claude-memory": {
      "command": "claude-memory-mcp",
      "args": []
    }
  }
}

CLI Reference

| Command | Description | |---------|-------------| | claude-memory init | Initialize the SQLite database | | claude-memory ingest [PATH] | Ingest session logs from path | | claude-memory ingest --watch | Watch and auto-ingest new sessions | | claude-memory search "query" | Hybrid semantic + keyword search | | claude-memory context [PROJECT] | Generate context summary | | claude-memory list | List all indexed sessions | | claude-memory stats | Database statistics | | claude-memory prune --older-than 90d | Remove old memories | | claude-memory export | Export memories as JSON | | claude-memory serve | Start MCP server mode |

Global Options

| Option | Description | |--------|-------------| | --config PATH | Custom config file path | | --verbose / -v | Enable debug logging | | --version | Show version |

Search Options

| Option | Description | |--------|-------------| | --project / -p | Filter by project path | | --category / -c | Filter by category | | --limit / -n | Max results (default: 5) |

MCP Setup

Claude Desktop

Find your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the memory server:

{
  "mcpServers": {
    "claude-memory": {
      "command": "claude-memory-mcp",
      "args": []
    }
  }
}

Restart Claude Desktop.

See examples/claude-desktop-config.json for a complete example.

MCP Tools

Once connected, Claude Desktop can use these tools:

| Tool | Description | |------|-------------| | memory_search | Search memories by query with optional filters | | memory_recall | Get a formatted context summary for a project | | memory_save | Save a new memory directly | | memory_stats | Get database statistics |

Architecture

claude-memory-manager/
  src/claude_memory/
    cli.py              # Click CLI commands
    mcp_server.py       # MCP stdio server
    config.py           # Configuration management
    core/
      extractor.py      # Memory extraction from conversations
      embedder.py       # Embedding generation + caching
      indexer.py         # Pipeline: parse -> extract -> embed -> store
      retriever.py      # Hybrid semantic + keyword search
      summarizer.py     # Context summary generation
    parsers/
      jsonl_parser.py   # Claude Code session log parser
      diff_parser.py    # Unified diff parser
    storage/
      database.py       # SQLite + FTS5 operations
      models.py         # Pydantic data models
      migrations.py     # Schema versioning
    integrations/
      anthropic_embeddings.py  # Voyage AI API
      local_embeddings.py      # sentence-transformers
    utils/
      formatting.py     # CLI output formatting
      license.py        # License validation

Data Flow

Session Logs (.jsonl)
        |
  [JSONL Parser] -----> ParsedSession
        |
  [Extractor] --------> Memory objects (categorized, scored)
        |
  [Embedder] ----------> Embeddings (bytes for SQLite BLOB)
        |
  [Indexer] -----------> SQLite DB (with FTS5 index)
        |
  [Retriever] ---------> Search results (hybrid ranked)
        |
  [Summarizer] --------> Context summary (markdown)

Configuration

Configuration is loaded from (in priority order):

Environment variables
Config file (~/.claude-memory/config.json)
Defaults

Environment Variables

| Variable | Description | Default | |----------|-------------|---------| | CLAUDE_SESSIONS_PATH | Path to session logs | ~/.claude/projects | | CLAUDE_MEMORY_DB_PATH | Database file path | ~/.claude-memory/memory.db | | CLAUDE_MEMORY_EMBEDDING_PROVIDER | anthropic, voyage, or local | local | | ANTHROPIC_API_KEY | Anthropic API key | — | | VOYAGE_API_KEY | Voyage AI API key | — | | CLAUDE_MEMORY_MAX_TOKENS | Max tokens for context | 2000 | | CLAUDE_MEMORY_LOG_LEVEL | Log level | INFO |

Embedding Providers

| Provider | Dimension | Requires | |----------|-----------|----------| | voyage | 1024 | VOYAGE_API_KEY | | anthropic | 1024 | ANTHROPIC_API_KEY | | local | 384 | pip install claude-memory-manager[local] |

If no provider is available, a stub provider is used (keyword search still works, but semantic search is disabled).

FAQ

Where are my memories stored? In a SQLite database at ~/.claude-memory/memory.db. All data stays local.

Does this send my code to any API? Only if you configure the Voyage or Anthropic embedding provider. In that case, only memory text content (not full session logs) is sent to generate embeddings. Use local for fully offline operation.

How does deduplication work? Each memory's content is hashed (SHA-256). If a memory with the same hash already exists, it is skipped during ingestion.

How does hybrid search work? Results from cosine-similarity vector search (70% weight) are combined with SQLite FTS5 keyword search results (30% weight). Memories appearing in both get combined scores.

Can I export my memories? Yes: claude-memory export > memories.json or claude-memory export -o file.json.

How do I prune old memories? claude-memory prune --older-than 90d removes memories older than 90 days. Supports d (days), w (weeks), m (months), y (years).

Development

# Clone and install in development mode
git clone https://github.com/nyxtools/claude-memory-manager.git
cd claude-memory-manager
pip install -e ".[dev]"

# Run tests
pytest

# Type check
mypy src/

# Lint
ruff check src/ tests/

claude-memory-manager