diff --git a/README.md b/README.md
index 1c5ba544..6cd629e3 100644
--- a/README.md
+++ b/README.md
@@ -37,14 +37,19 @@ Deploy anywhere. Own your data. Control your AI stack.
 
 ## Key Features
 
-- **Unify your Data for Reliable, Accurate, and Precise AI**
-- **Ship Intelligent Agents Powered with Your Data**
-- **Connect Your Agents with MCP**
-- **Run Anywhere**
-- **Observe Your Data**
+- **Ontology-Driven Context Engineering**
+- **Unify Data Silos for Reliable, Accurate, and Precise AI**
+- **Automated Knowledge Graph Construction and Retrieval**
+- **Single Agent or Multi-Agent Systems**
+- **Interoperability with MCP**
+- **Run Anywhere from local to cloud**
+- **Observability and Telemetry**
 - **Serve Models for Private LLM Inference**
-- **Create Many Workflows**
-- **Control Data Access**
+- **Create Custom Workflows**
+- **Control Data Access for Users and Agents**
+- **Backend Orchestration for Knowledge Graphs, Datastores, and File and Object Storage**
+- **High Throughput Data Streaming**
+- **Fully Containerized**
 
 ## Why TrustGraph?
 
@@ -99,6 +104,14 @@ The **Workbench** provides tools for all major features of TrustGraph. The **Wor
 - **Agent Tools**: Define tools with collections, knowledge cores, MCP connections, and tool groups
 - **MCP Tools**: Connect to MCP servers
 
+## TypeScript Library for UIs
+
+There are 3 libraries for quick integration of TrustGraph services to a frontend.
+
+- [@trustgraph/client](https://www.npmjs.com/package/@trustgraph/client)
+- [@trustgraph/react-state](https://www.npmjs.com/package/@trustgraph/react-state)
+- [@trustgraph/react-provider](https://www.npmjs.com/package/@trustgraph/react-provider)
+
 ## Knowledge Cores
 
 A challenge facing GraphRAG architectures is the ability to reuse and remove datasets from agent workflows. TrustGraph can store the data ingest process as reusable Knowledge Cores. Knowledge cores can be loaded and removed during runtime. Some sample knowledge cores are [here](https://github.com/trustgraph-ai/catalog/tree/master/v3).