TLDR: Graphwise, also known as Ontotext AD, has launched GraphDB 11, a significant upgrade to its graph database designed to serve as the intelligent core for AI agents. The new version enhances enterprise knowledge management, improves AI model reliability, and reduces infrastructure costs by integrating structured and unstructured data through a semantic layer and supporting advanced protocols like MCP and GraphQL.
Graphwise, officially known as Ontotext AD, a prominent Bulgarian graph database startup, announced on July 8, 2025, a major upgrade to its flagship GraphDB tool with the release of GraphDB 11. This latest iteration is specifically engineered to bolster enterprise knowledge management and establish a more robust foundation for artificial intelligence models, positioning itself as the ‘brains’ of AI agents.
GraphDB is a specialized graph database that excels at storing contextual data alongside traditional business records, enabling the discovery of complex connections that are often challenging with conventional Structured Query Language (SQL) databases. The core enhancement in GraphDB 11 is its ability to bridge the gap between raw data and actionable knowledge, crucial for augmenting the capabilities of large language models (LLMs). It achieves this by creating an ‘intelligent fabric’ that seamlessly connects content and data.
Key features introduced in GraphDB 11 include a sophisticated ‘semantic layer’ capable of managing both structured data and unstructured content while maintaining semantic consistency. The platform leverages a ‘knowledge graph’ that provides a dynamic, interconnected view of enterprise content, encoding relationships, hierarchies, and metadata. This allows AI models to better understand user intent, suggest related topics, and support scenario-based recommendations, for instance, by auto-tagging documents with user-specified taxonomies and content-derived semantics.
A significant advancement is the support for the Model Context Protocol (MCP), which enables AI agents to directly tap into GraphDB’s knowledge graph. This grounding in relevant domain data is expected to result in more reliable, accurate, and context-aware AI agents, enhancing their decision-making abilities and boosting efficiency across various workflows. Furthermore, Graphwise has improved its ‘precision entity linking,’ which accurately maps user-inputted terms and phrases to the correct concepts within the knowledge graph, thereby eliminating ambiguity and refining information retrieval for AI model outputs.
GraphDB 11 also addresses the critical need for cost reduction in AI infrastructure. It introduces support for the GraphQL language, simplifying data access for developers, even those without extensive graph technology backgrounds. The company also claims higher availability and performance optimizations, including advanced repository caching, which boosts scalability and responsiveness, making the platform more cost-effective. The improved ‘Talk to Your Graph’ feature empowers GraphRAG (Retrieval-Augmented Generation), enabling natural language access to enterprise knowledge graphs, which helps businesses reduce ‘hallucinations’ and improve accuracy in AI-driven decisions.
Atanas Kiryakov, President of Graphwise, highlighted the industry challenge GraphDB 11 aims to solve. ‘Enterprise organizations continue to struggle with AI project abandonment due to a lack of AI-ready data, a significant challenge reflected in Gartner’s prediction that through 2026, 60% of AI projects will face this very fate,’ Kiryakov stated. ‘GraphDB 11 directly addresses this by delivering the data infrastructure and governance that is essential for cutting-edge AI, including generative AI. We empower customers to build intelligent, scalable applications by making their complex, unstructured data accessible and actionable through precise domain knowledge and robust reasoning.’
Also Read:
- Google AI Releases Open-Source MCP Toolbox to Enhance Secure Database Access for AI Agents
- Denodo Unveils DeepQuery: Advancing AI with Enterprise-Wide Deep Research Capabilities
Industry experts have also lauded the release. Michael Ni, an analyst at Constellation Research Inc., commented to SiliconANGLE that ‘GraphDB 11 is a promising release that raises the bar in terms of what AI-ready enterprise data must deliver. By combining knowledge graphs with semantic reasoning and simplifying LLM integration and orchestration, Graphwise delivers a trust layer that grounds AI in how your business works. This isn’t just another graph release — it’s a rising blueprint and a delivered simplification for context-aware, decision-ready AI that we will see other enterprise platforms follow.’
