🔥 3 days trending on GitHub in a row. 1,700+ stars and counting for TrustGraph — the open-source context development platform. Graph-native. Grounded. Built for agents that actually need to know things. Thank you to every dev who starred, forked, and built with us. 🙏

x.com/i/article/2037…

The biggest problem with RAG in production: you don't know why your AI said that. TrustGraph 2 fixes that with full-stack explainability. Here's how it works At ingest time, TrustGraph emits PROV-O triples tracing every fact back to its source — document → page → chunk →

Most AI stacks hide a dirty secret: swap your LLM provider, and everything breaks. TrustGraph was built differently. TrustGraph ships with a full, modular LLM inferencing stack — so you're never locked into a single model or provider. Whether you're running fully air-gapped

Did you know TrustGraph has a full LLM inferencing stack? TrustGraph is a lot more than just the leading context graph technology, it's your complete context operating system.

Another milestone! 🎉 🌟 Not long ago, we celebrated 1,000 🌟 — and the momentum since then has been incredible. After spening nearly an entire week trending on GitHub, we celebrate 2,000 🌟! This isn't just a vanity metric. Every star represents a developer, researcher, or

Another milestone for TrustGraph! Thanks to everyone building with the context operating system for AI, leveraging the true power of context graph technology. #RealContextGraphs #ContextGraph

TrustGraph v2.2 is live. 🚀 Multi-pattern agent orchestration. RabbitMQ pub/sub. SPARQL 1.1 query service. Universal document decoder. Big release. Here's what's in it 🧵

One document decoder to rule them all 📄 DOCX, XLSX, PPTX, HTML, Markdown, CSV, EPUB, ODT, RTF — unified pipeline, configurable chunking, tables preserved as HTML.

For everyone that has called out #ApachePulsar as a blocker for integrating TrustGraph into your estate, version 2.2 is for you! TrustGraph now features native support for RabbitMQ which offers a massive **20%** reduction in total footprint! As big as that is, oh by the

What are ontologies and how are they relevant to context graphs?

Ontologies provide interoperable context structures that deep learning models (LLMs) lack.

TrustGraph - Graph-native AI context platform (TrustGraph) Cossmology Profile: dub.sh/yDcLAoc Key People: Daniel Davis (Daniel Davis), Mark Adams (@Cybermaggedon) #KnowledgeGraph #OpenSource #OSS #COSS

TrustGraph 2.3 is live 🎉 What's new: - Processor Groups → up to 2.5 GB memory savings per install - RabbitMQ production-ready → another ~1 GB saved - Kafka backend (beta) - amd64 + arm64 multi-arch containers - LLM token usage exposed end-to-end for cost tracking - Ontology

Launch 2.3 today: github.com/trustgraph-ai/…

With every release TrustGraph becomes leaner, more efficient, and more flexible. 💪 Not only is RabbitMQ support production ready in release 2.3, but beta support for Kafka is live. Now TrustGraph provides you the flexibility of three messaging fabrics: Pulsar, RabbitMQ, or

How ontologies like W3C PROV-O are the foundation of explainable AI.

I'm so glad in my recent episode of Knowledge Graph Insights with Larry Swanson, that I finally got to talk about something that's been overlooked - The timeline of the explosion of the term context graph. Yes, it started with the Foundation Capital article, but what happened

It's easy to laugh at Ask Jeeves, but their core thesis was correct - people wanted to search with natural language questions, not keywords and boolean operators. They were just too early. There are lot of flawed theses in AI at the moment as well.

Working on some new content for explaining how natural language becomes graph structures for scalable context graph systems, and it occurred to me how similar the process is to sentence diagramming. But is diagramming sentences even taught anymore? Do people even know what I'm