gymaira1990-jpg opened a new issue, #2447: URL: https://github.com/apache/age/issues/2447
## Mnemosyne OS — Production use case with Apache AGE knowledge graph Hi AGE team! We're building a cognitive memory OS for AI agents, and Apache AGE is our knowledge graph backbone. Wanted to share as a real-world use case. ### How we use AGE **Mnemosyne OS v5.2** uses AGE's Cypher engine for entity relationship reasoning: - Auto-extracts entities from conversation memories - Builds Cypher graphs (`mnemosyne_graph`) with MERGE/CREATE patterns - Multi-hop graph search via `POST /api/v1/graph/search` - 3 ag_labels: `_ag_label_vertex`, `_ag_label_edge`, `Entity` ### Architecture - PostgreSQL 16 + pgvector (1024d) + Apache AGE 1.6.0 - 5-level Time Memory Tree with LLM auto-distillation - 3-Hall knowledge pipeline (Research→Engineering→Archive) - Runs 7x24 on Tencent Cloud · FastAPI + asyncpg ### Links - GitHub: https://github.com/gymaira1990-jpg/Mnemosyne-OS - Whitepaper: https://doi.org/10.5281/zenodo.20837834 - Website: https://my.g-cat.cn Happy to contribute AGE usage patterns or feedback back to the project! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
