TrustGraph provides an event-driven data-to-AI platform that transforms raw data into AI-ready datasets through automated structuring, knowledge graph construction, and vector embeddings mapping — all deployable privately, on-prem, or in your cloud. Deploy and manage open LLMs within the same platform, ensuring complete data sovereignty while enabling agents that generate real, actionable insights.
TrustGraph is not just another AI framework but a complete, production-ready platform that bridges the gap between raw data and intelligent, adaptable agent deployments.
- **AI-Ready Data Transformation**: Convert unstructured and structured (bring your own schema) data into AI-optimized formats.
- **Automated Knowledge Graph Construction**: Transform unstructured data into interconnected knowledge graphs that capture relationships, context, and meaning.
- **Semantic Retrieval**: TrustGraph combines multiple retrieval methods optimized for each data type and use case.
- **Event Driven**: Built with Apache Pulsar for high-throughput and reliable messaging
- **Datastore Orchestration**: Deploy stores like Apache Cassandra, Neo4j, Qdrant, Milvus, Memgraph, or FalkorDB for structured and unstructured data storage.
- **Data Sovereignty**: Deploy the entire stack—data pipelines, knowledge graphs, vector stores, and LLMs—on-premises, in your VPC, or across hybrid environments.
- **Private LLM Inferencing**: In addition to support for all major LLM APIs, deploy and manage open models connected to all of the agentic data infrastructure.
- **Agentic GraphRAG**: Deploy intelligent agents with context awareness. Bring your own ontology for easy integration into interconnected systems.
- **Production Ready**: Containerized deployment with Docker/Kubernetes support. Built for enterprise scale with monitoring, observability, and management.
- **MCP Integration**: Native support for MCP enables standardized agent communication with third-party tools and services while maintaining data sovereignty.
- **Full Stack Visibility**: 3D visualization of knowledge graphs. Grafana dashboard for observability.
The [**Configuration Builder**](https://config-ui.demo.trustgraph.ai/) assembles all of the selected components and builds them into a deployable package. It has 4 sections:
- **Component Selection**: Choose from the available deployment platforms, LLMs, graph store, VectorDB, chunking algorithm, chunking parameters, and LLM parameters
The **Workbench** is a UI that provides tools for interacting with all major features of the platform. The **Workbench** is enabled by default in the **Configuration Builder** and is available at port `8888` on deployment. The **Workbench** has the following capabilities:
TrustGraph features a complete context engineering solution combinging the power of Knowledge Graphs and VectorDBs. Connect your data to automatically construct Knowledge Graphs with mapped Vector Embeddings to deliver richer and more accurate context to LLMs for trustworthy agents.
- **Automated Knowledge Graph Construction:** Data Transformation Agents processes source data to automatically **extract key entities, topics, and the relationships** connecting them. Vector emebeddings are then mapped to these semantic relationships for context retrieval.
- **Deterministic Graph Retrieval:** Semantic relationsips are retrieved from the knowledge graph *without* the use of LLMs. When an agent needs to perform deep research, it first performs a **cosine similarity search** on the vector embeddings to identify potentially relevant concepts and relationships within the knowledge graph. This initial vector search **pinpoints relevant entry points** within the structured Knowledge Graph which gets built into graph queries *without* LLMs that retrieve the relevant subgraphs.
- **Context Generation via Subgraph Traversal:** Based on the ranked results from the similarity search, agents are provided with only the relevant subgraphs for **deep context**. Users can configure the **number of 'hops'** (relationship traversals) to extend the depth of knowledge availabe to the agents. This structured **subgraph**, containing entities and their relationships, forms a highly relevant and context-aware input prompt for the LLM that is endlessly configurable with options for the number of entities, relationships, and overall subgraph size.
One of the biggest challenges currently facing RAG architectures is the ability to quickly reuse and integrate knowledge sets like long-term memory for LLMs. **TrustGraph** solves this problem by storing the results of the data ingestion process in reusable Knowledge Cores. Being able to store and reuse the Knowledge Cores means the data transformation process has to be run only once. These reusable Knowledge Cores can be loaded back into **TrustGraph** and used for GraphRAG. Some sample knowledge cores are available for download [here](https://github.com/trustgraph-ai/catalog/tree/master/v3).
When a Knowledge Core is loaded into TrustGraph, the corresponding graph edges and vector embeddings are queued and loaded into the chosen graph and vector stores.
