Blogsby Glyphcognee 1.0
cognee 1.0 is live: open-source memory for AI agents, now self-improving, with a Rust core and single-Postgres deployment. Cognee is a dltHub partner that uses dlt under the hood for loading structured data.
9 of 800 posts
Fri Jun 261 post
Wed Jun 241 post
What is the dltHub Context Layer?
Continuous context: Less manual input, more agent autonomy.
Tue Jun 161 post
The rise of the Semantic engineer
As pipelines, models, and dashboards become generated and disposable, the scarce input shifts from technical skill to business meaning, and a new role emerges
Tue Jun 91 post
Text-to-SQL is a definition problem: build the canonical model first
Text-to-SQL doesn’t break because models can’t write SQL. It breaks because they don’t know what your data means. Write the meaning down first as a canonical knowledge layer, and use that one spec to both build the model and answer...
Mon Jun 81 post
Why LLMs Get the Right Answer for the Wrong Reason
Schema alone scored 3/10. An ontology scored 10/10. A benchmark across two datasets showing exactly where the gap is.
Fri Jun 51 post
Schema evolution in data pipelines: the engineer's guide
Schema evolution is a decision every data pipeline makes, and most tools make it silently. This post discusses the five common failure modes every data pipeline sees, how dlt handles them, and how you can decide runtime policies for schema...
Tue Jun 21 post
dltHub Named 2026 Snowflake Startup Program Product Partner of the Year
dltHub has been named the 2026 Snowflake Startup Program Product Partner of the Year for helping more than 1,000 organizations ingest complex data into the Snowflake AI Data Cloud with Python-native, AI-driven pipelines.
Mon Jun 12 posts
dltHub AI Workbench data quality toolkit: schema-aware checks that route their own fixes
Preview of the dltHub AI Workbench data quality toolkit: schema-bootstrapped checks, column sampling before any rule ships, decorators that run inside pipeline.run(), and routing of failures back to the toolkit that owns the surface area.
Benchmarking dlthub: SQL, REST, JSON, Parquet, & MongoDB to BigQuery
What an hour of compute moves with dltHub, measured across four bottlenecks: 170 GB/hr Parquet, 65 GB/hr SQL, 4.6 GB/hr messy JSON, and REST paced by the API.