Happy slice of mcp pizzaMCP.pizza

genesys

MCP.Pizza Chef: Astrix-Labs

Genesys adds a smart memory layer to your AI that not only remembers facts but also why they happened. It organizes memories as connected causes and effects, helping your AI recall relevant information and forget what’s no longer important. It works with apps like Claude Desktop and ChatGPT, but requires some developer setup to install and run locally. No API keys are needed for basic use.

Other

Use This MCP server To

Help my AI remember reasons behind its past decisions Recall important past information with context Search memories by topic or date Forget outdated or irrelevant memories automatically Explain why the AI made a certain choice Connect related memories to understand cause and effect Keep AI memory manageable and relevant over time

README

PyPI PyPI Downloads CI License: AGPL v3

Genesys

The intelligence layer for AI memory.

Genesys doesn't just remember what happened; it remembers why. A scoring engine + causal graph + lifecycle manager for AI agent memory. Speaks MCP natively.

LoCoMo benchmark (certified)

System Score Protocol
Genesys Memory 85.55 ± 0.37 Frozen: gpt-4o-mini answerer + judge, temp 0, n=1,540, cats 1–4, 10 runs (July 2026)
Zep 75.14 Comparable published setup
Mem0 66.9 Comparable published setup (Mem0 paper)

Self-reported vendor figures above ~90 use different answerers/judges and are not comparable — the oracle retrieval ceiling under this frozen protocol is 94.9. Reproduce it yourself: Astrix-Labs/locomo-harness · full methodology · per-run results.

Hosted product: genesys.astrixlabs.ai — your personal memory for AI, carried across ChatGPT, Claude, and every MCP app · Pricing · Developer docs · Benchmark methodology (85.55 on LoCoMo, certified over 10 runs, receipts published) image

What is this

genesys FAQ

Can I use this to help my AI remember why it made decisions?
Yes — Genesys stores memories with causes, so your AI understands why it chose something.
Can I use this with ChatGPT or Claude Desktop?
Yes — it works with both Claude Desktop and ChatGPT through MCP.
Do I need an API key or account to use Genesys?
No — the basic package runs locally without needing any API keys or accounts.
Is it easy to set up Genesys?
It requires developer-level setup, including installing with pip and running a local server.
Does Genesys store memories permanently?
By default, it keeps memory in your computer’s memory or optionally in JSON files; it doesn’t need a database.
What happens if Genesys temporarily fails during use?
It handles errors gracefully so your AI keeps working without crashing.
Can I search and recall memories with Genesys?
Yes — you can ask your AI to recall or search memories naturally, including filtering by date or category.