rishimeka

Genesys — AI skill for Claude Code

AI community

Open-source causal graph memory for AI agents.

How to install Genesys

This entry records only its repository, not the path inside it, so there is no exact command to give. Open rishimeka/genesys and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Genesys does

Open-source causal graph memory for AI agents. 89.9% on LoCoMo. MCP server with ACT-R scoring, spreading activation, and active forgetting.

Alternatives in AI

Invisible Dots — Open-source, self-hosted alternative to OpenAI Dots, Meta Muse, Grok Bot, Manus Cue and Claude Cowork 31.8k ★
AIHawk — Open-source AI browser agent: describe any task in plain language and it autonomously browses, clicks, types a 30.3k ★
Osaurus — Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cry 5.1k ★

README

[![PyPI](https://img.shields.io/pypi/v/genesys-memory)](https://pypi.org/project/genesys-memory/) [![PyPI Downloads](https://img.shields.io/pypi/dm/genesys-memory)](https://pypi.org/project/genesys-memory/) [![CI](https://github.com/Astrix-Labs/genesys/actions/workflows/ci.yml/badge.svg)](https://github.com/Astrix-Labs/genesys/actions/workflows/ci.yml) [![License: AGPL v3](https://img.shields.io/badge/License-AGPL_v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0)

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](https://github.com/Astrix-Labs/locomo-harness) · [full methodology](https://genesys.astrixlabs.ai/developers/methodology) · [per-run results](https://genesys.astrixlabs.ai/benchmarks/locomo).

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