Mnemograph

Mnemograph

A persistent, event-sourced knowledge graph for AI coding agents. Unlike simple key-value memory, Mnemograph captures entities, relations, and observations — enabling semantic search, tiered context retrieval, and git-based version control of your AI's memory.

Works with: Claude Code, opencode, codex CLI, Zed, Continue.dev, and any MCP-compatible agent.

Why Mnemograph?

AI coding sessions are ephemeral. Mnemograph gives your AI partner persistent memory that:

• Survives across sessions — decisions, patterns, learnings persist
• Supports semantic search — find relevant context by meaning, not just keywords
• Provides tiered retrieval — shallow summaries to deep subgraphs based on need
• Versions like code — branch, commit, diff, revert your knowledge graph
• Enables collaboration — share memory repos across users or projects

Memory Scope: Local vs Global

Before using mnemograph, decide where to store memory:

Important: Agents should ask the user which scope to use when first setting up mnemograph for a project. This affects where knowledge is stored and whether it's shared across projects.

# Project-local (default)MEMORY_PATH=".claude/memory"
# Global (cross-project)MEMORY_PATH="$HOME/.claude/memory"
# CLI: use --global flagmnemograph --global statusmnemograph --global graph

Quick Start

Option 1: Let Claude Code install it

Give Claude Code this repo URL and ask it to set up mnemograph:

https://github.com/tm42/mnemograph

Or point Claude to the setup instructions directly:

Read https://raw.githubusercontent.com/tm42/mnemograph/main/SETUP_CLAUDE_CODE.md and follow them

Option 2: Manual installation

# Install from PyPIpip install mnemograph
# Add to Claude Code (global, available in all projects)claude mcp add --scope user mnemograph \  -e MEMORY_PATH="$HOME/.claude/memory" \  -- uvx mnemograph
# Initialize memory directorymkdir -p ~/.claude/memory

Option 3: Other MCP Clients

Each MCP client has a different configuration format. See UNIVERSAL_MCP_COMPATIBILITY.md for copy-paste configs for:

• opencode — ~/.config/opencode/opencode.json
• Codex CLI — ~/.codex/config.yaml
• Zed — ~/.config/zed/settings.json
• Continue.dev — ~/.continue/config.json

The key environment variable is MEMORY_PATH — set it to where you want the knowledge graph stored.

Option 4: Install from source

git clone https://github.com/tm42/mnemograph.gitcd mnemographuv sync
# Add to Claude Code (or adapt for your MCP client)claude mcp add --scope user mnemograph \  -e MEMORY_PATH="$HOME/.claude/memory" \  -- uv run --directory /path/to/mnemograph mnemograph

Usage

MCP Tools (used by any agent)

Mnemograph exposes these tools via MCP:

Core Operations:

Session Lifecycle:

Branching (Parallel Workstreams):

Graph Maintenance:

Time Travel:

Edge Weights:

Recall: Prose vs Graph Format

The recall tool returns context in prose format by default — human-readable text that agents can consume directly without parsing JSON:

# Default: prose format (human-readable)recall(depth="medium", query="authentication")# Returns:# **MyApp** (project)# A Python web service. Uses OAuth2 for user auth.# Uses: PostgreSQL, Redis## **Decisions:**# • Decision: Use JWT — Stateless tokens for API authentication## **Gotchas:**# • Token expiry is 1 hour by default# • Refresh tokens stored in Redis
# Optional: graph format (structured JSON)recall(depth="medium", query="authentication", format="graph")

Depth levels:

• shallow — Quick summary: entity counts, recent activity, gotchas
• medium — Semantic search + 1-hop neighbors (~2000 tokens)
• deep — Multi-hop traversal from focus entities (~5000 tokens)

Gotcha extraction: Observations prefixed with Gotcha:, Warning:, Note:, or Important: are automatically extracted into a dedicated section.

CLI Tools

mnemograph — Unified CLI for all memory operations:

# Basic operationsmnemograph status                # Show entity/relation counts, recent eventsmnemograph log                   # View event historymnemograph log --session X       # Filter by sessionmnemograph sessions              # List all sessionsmnemograph export                # Export graph as JSON
# VCS commands (git-based version control)mnemograph vcs init              # Initialize memory as git repomnemograph vcs commit -m "msg"   # Commit current statemnemograph vcs log               # View commit historymnemograph vcs revert --event ID # Undo specific events (compensating events)mnemograph vcs revert --session X # Undo entire session
# Graph visualizationmnemograph graph                 # Open interactive graph viewermnemograph graph --watch         # Live reload mode (refresh button)
# Time travelmnemograph show --at "2 days ago"  # View state at a point in timemnemograph diff "1 week ago"       # Show changes since thenmnemograph history "EntityName"    # Full changelog for an entitymnemograph rewind -n 1             # Git-based rewind by N commitsmnemograph restore --to "yesterday" # Event-based restore (audit-preserving)
# Graph health and maintenancemnemograph health                # Show graph health report (orphans, duplicates, etc.)mnemograph health --fix          # Interactive cleanup modemnemograph similar "React"       # Find entities similar to "React" (duplicate check)mnemograph orphans               # List entities with no relationsmnemograph suggest "FastAPI"     # Suggest relations for an entitymnemograph clear                 # Clear all entities and relations (with confirmation)
# Global options (come *before* the subcommand)mnemograph --global status       # Use global memory (~/.claude/memory)mnemograph --memory-path /path graph  # Custom memory location

Running from anywhere (without activating the venv):

# Using uv (recommended)uv run --directory /path/to/mnemograph mnemograph graph
# Using uvx (if installed from PyPI)uvx --from mnemograph mnemograph status

Graph Visualization — Interactive D3.js viewer:

• Layout algorithms: Force-directed, Radial (hubs at center), Clustered (by component)
• Color modes: By entity type, connected component, or degree centrality
• Edge weight slider: Filter connections by strength
• Live refresh: --watch mode with Refresh button for real-time updates

Architecture

~/.mnemograph/memory/    # or ~/.claude/memory, ~/.opencode/memory, etc.├── mnemograph.db        # SQLite database (events + vectors)├── state.json           # Cached materialized state (derived)└── .git/                # Version history

Event sourcing means all changes are recorded as immutable events in SQLite. The current state is computed by replaying events. This enables:

• Full history of all changes
• Revert any operation
• Branch/merge knowledge graphs
• Audit trail of what Claude learned and when

Two-layer versioning:

• mnemograph vcs revert — fine-grained, undo specific events via compensating events
• mnemograph rewind / mnemograph restore — coarse-grained, git-level or timestamp-based restore

Branching

Branches let you work on isolated knowledge without affecting the main graph. Perfect for:

• Exploratory work — try approaches without polluting shared knowledge
• Feature-specific context — "feature/auth-refactor" keeps auth decisions separate
• Multiple projects — switch context between different codebases

Creating and Using Branches

# Create a branch for your featurecreate_branch(name="feature/auth-refactor")
# Work normally — all operations happen on this branchremember(name="OAuth2", entity_type="concept",         observations=["Implementing OAuth2 flow"])
# Switch back to main to see clean stateswitch_branch(name="main")
# Merge when readymerge_branch(source="feature/auth-refactor", target="main")

How Branching Works

• Main branch always exists, contains shared knowledge
• Feature branches inherit from main but additions stay isolated
• Automatic filtering — recall, search, etc. only see current branch + main
• Merge copies branch entities/relations into target branch
• Delete cleans up after merge (or abandons exploratory work)

Branch Naming Conventions

Entity Types

Topic Convention

Use topic entities as entry points for browsing related knowledge:

# Create topic entry pointscreate_entities([    {"name": "topic/projects", "entityType": "entity"},    {"name": "topic/decisions", "entityType": "entity"},    {"name": "topic/patterns", "entityType": "entity"},])
# Link entities to their topicscreate_relations([    {"from": "auth-service", "to": "topic/projects", "relationType": "part_of"},    {"from": "Decision: Use Redis", "to": "topic/decisions", "relationType": "part_of"},])

Standard topics:

• topic/projects — Project entities
• topic/decisions — Architectural decisions
• topic/patterns — Patterns and practices
• topic/learnings — Key discoveries
• topic/questions — Open questions

This makes it easy to query "what decisions have we made?" by exploring topic/decisions.

Development

git clone https://github.com/tm42/mnemograph.gitcd mnemographuv sync                    # Install dependenciesuv run pytest --cov        # Run tests with coverage (enforces 75% minimum)uv run ruff check .        # Lintuv run mnemograph          # Run MCP server directly

Based On

Mnemograph builds on MCP server-memory — Anthropic's official memory server

License

MIT