Oracle Database

Oracle Agent Memory is a Python SDK that provides a persistent agent memory layer using Oracle Database multi-model primitives. It supports memory formation, recall, evolution, evaluation, governance, and feedback, with typed episodic, semantic, procedural, and working memories. Its storage schema combines vectors, text indexes, graph links, timestamps, and audit history; memory formation includes redaction before writing, while recall uses hybrid search across multiple retrieval methods and feedback supports handling stale, poisoned, or conflicting memories. The SDK is presented with a Python notebook as a hands-on walkthrough.

Oracle AI Developer Hub is an actively maintained open-source repository of technical resources for building AI applications, agents, and systems with Oracle AI Database and OCI services. It covers working applications, Jupyter notebooks, architecture and memory guides, partner integrations, and hands-on workshops spanning vector search, RAG, multi-agent orchestration, persistent agent memory, hybrid retrieval, and database-backed AI systems. Examples include applications and tutorials using vector, text, graph, spatial, relational, and JSON capabilities, as well as agent checkpoints, long-term memory, semantic caches, and MCP integrations. The repository is maintained by Oracle and community contributors, and is licensed under the Universal Permissive License, Version 1.0.

DBOS is a database-oriented operating-system project and application environment that stores important system state in a database. Its practical focus includes durable, recoverable workflows, particularly workflows used by agentic AI systems.

Neo4j Agent Memory is a graph-native memory system for AI agents developed as a Neo4j Labs project. It stores conversations and messages as short-term memory, builds long-term knowledge graphs using the POLE+O model, and records entities, relationships, reasoning traces, tool usage, decisions, preferences, and facts for later retrieval. The system combines vector and text search, entity resolution and deduplication, similar-task retrieval, multi-stage entity and relationship extraction, background enrichment, and geospatial queries. Python and TypeScript clients support hosted NAMS usage or direct connections to Neo4j and Neo4j AuraDB through Bolt. An MCP server exposes capabilities for searching memory, retrieving context, storing messages, managing entities and preferences, inspecting graph data, and recording reasoning. Neo4j Labs describes it as actively maintained but not officially supported.

Oracle is an enterprise system of record to which invoice and procurement information can be pushed. In the cited procurement context, it represents the incumbent software layer where final purchasing data is recorded, while surrounding work may involve emails, spreadsheets, supplier discussions, analyses, and operational decisions.