Genesys Memory

Name: Genesys Memory
Author: rishimeka

by rishimekacommunityv0.3.11

Genesys is an MCP-native memory layer for AI agents that scores memories, links them in a causal graph, and prunes them over time. It can run with in-memory storage, Postgres/pgvector, an Obsidian vault, or FalkorDB.

From the registry: Causal graph memory engine for AI agents with scoring, activation, and forgetting

GitHub Repository

Install & configure

Prerequisites

required
Install genesys-memory
Install the Python package. The README recommends the in-memory option for most users as the simplest setup.
```
$ pip install genesys-memory
```
https://pypi.org/project/genesys-memory/
required
Set API key or use local embedder
By default, Genesys uses OpenAI embeddings, so you must set OPENAI_API_KEY unless you configure GENESYS_EMBEDDER=local. The fully local path in the README is shown for the Obsidian backend.

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `genesys-memory` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install genesys-memory** — Install the Python package. The README recommends the in-memory option for most users as the simplest setup. Run: `pip install genesys-memory` (https://pypi.org/project/genesys-memory/)
- **Set API key or use local embedder** — By default, Genesys uses OpenAI embeddings, so you must set OPENAI_API_KEY unless you configure GENESYS_EMBEDDER=local. The fully local path in the README is shown for the Obsidian backend.

Canonical MCP server config (HTTP transport):
- url: `http://<host>:<port>/mcp`

Note: Genesys is an HTTP MCP server started separately, typically with `uvicorn genesys.api:app --port 8000`, then connected at `/mcp`. Simplest default setup is the in-memory backend with no extra backend env vars. Relevant runtime env vars from the README: OPENAI_API_KEY (required unless GENESYS_EMBEDDER=local), ANTHROPIC_API_KEY (optional), GENESYS_BACKEND (optional; default `memory`), GENESYS_EMBEDDER (optional; default `openai`), DATABASE_URL (required if GENESYS_BACKEND=postgres), OBSIDIAN_VAULT_PATH (required if GENESYS_BACKEND=obsidian unless auto-detected), FALKORDB_HOST (required if GENESYS_BACKEND=falkordb), GENESYS_USER_ID (optional), GENESYS_PERSIST_PATH (optional, for in-memory persistence).

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.

Note: Genesys is an HTTP MCP server started separately, typically with `uvicorn genesys.api:app --port 8000`, then connected at `/mcp`. Simplest default setup is the in-memory backend with no extra backend env vars. Relevant runtime env vars from the README: OPENAI_API_KEY (required unless GENESYS_EMBEDDER=local), ANTHROPIC_API_KEY (optional), GENESYS_BACKEND (optional; default `memory`), GENESYS_EMBEDDER (optional; default `openai`), DATABASE_URL (required if GENESYS_BACKEND=postgres), OBSIDIAN_VAULT_PATH (required if GENESYS_BACKEND=obsidian unless auto-detected), FALKORDB_HOST (required if GENESYS_BACKEND=falkordb), GENESYS_USER_ID (optional), GENESYS_PERSIST_PATH (optional, for in-memory persistence).

Tools (11)

memory_store

Store a new memory, optionally linking to related memories

memory_recall

Recall memories by natural language query using vector and graph signals

memory_search

Search memories with filters such as status, date range, and keyword

memory_traverse

Walk the causal graph from a given memory node

memory_explain

Explain why a memory exists and its causal chain

memory_stats

Get memory system statistics

pin_memory

Pin a memory so it is never forgotten

unpin_memory

Unpin a previously pinned memory

delete_memory

Permanently delete a memory

list_core_memories

List core memories, optionally filtered by category

set_core_preferences

Set user preferences for core memory categories

Environment variables

OPENAI_API_KEYrequiredUsed for embeddings unless GENESYS_EMBEDDER=local

DATABASE_URLrequiredPostgres connection string when using the postgres backend

OBSIDIAN_VAULT_PATHrequiredPath to the Obsidian vault when using the obsidian backend

FALKORDB_HOSTrequiredHost for FalkorDB when using the falkordb backend

Packages

genesys-memory

pypiv0.3.11transport: stdio

Details

Language: Python
License: AGPL-3.0
Released: Apr 25, 2026
Last commit: May 23, 2026
Registry name: io.github.rishimeka/genesys-memory

Related Servers

Claude Flow

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

68.0k

Codebase Memory Mcp

Persistent codebase knowledge graph. Survives session restarts and context compaction.

39.2k

Serena

A powerful toolkit for coding, providing semantic retrieval and editing capabilities.

28.1k