Mnemograph is a persistent, event-sourced knowledge graph designed for AI coding agents, capturing entities, relations, and observations for enhanced semantic search and context retrieval.
From the registry: Event-sourced knowledge graph memory for AI coding agents with semantic search
$ pip install mnemographPlease install the `mnemograph` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install mnemograph** — pip install mnemograph Run: `pip install mnemograph` (https://pypi.org/project/mnemograph/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["mnemograph"]
- optional environment variables:
- `MEMORY_PATH`: Path to knowledge graph storage (example: `$HOME/.claude/memory`)
Note: Event-sourced persistent knowledge graph for AI agents with git-based version control.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MEMORY_PATHrequiredPath where the knowledge graph is stored.MCP server for searching Airweave collections with natural language queries.