Please turn JavaScript on
Find more feeds
TiDB icon

TiDB

follow.it gives you an easy way to subscribe to TiDB's news feed! Click on Follow below and we deliver the updates you want via email, phone or you can read them here on the website on your own news page.

You can also unsubscribe anytime painlessly. You can even combine feeds from TiDB with other site's feeds!

Title: TiDB, Powered by PingCAP

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.3 / day

Message History

Different Starting Points, One Data Foundation: What’s New in TiDB Cloud
Key Takeaways TiDB Cloud Premium is announced for general availability, with customer availability in November 2026. BYOC and TiDB Cloud Filesystem enter public preview: managed TiDB Cloud in your own cloud account, and a persistent workspace for AI agents. PostgreSQL support on TiDB Cloud Starter opens in public prev...

Read full story
Persistent AI Agent Memory Explained: How Agents Remember Across Sessions
Key Takeaways Persistent agent memory is an external storage layer, not a bigger context window. Agents need episodic, semantic, and procedural memory, kept current by a capture-to-update loop. Claude Code, Codex, and Dify can share one durable state layer. Vector search alone is not enough. Production memory needs scope, metadata, and consistency....

Read full story
Why Open Source Still Matters When Agents Write the Code

Maintainers of well-known open source projects are dealing with a new kind of inbox. Pull requests still arrive, often in higher volume than ever, and many are clean, well-formatted, and plausible on first read. What changed is that one...


Read full story
The Database Is the Product: What Breaks When Memory Devices Scale

Editor’s note: This post originally appeared on The New Stack and is republished with permission. The original version is available here.

Key Takeaways Splitting metadata (MySQL) from content (S3) with no shared transaction boundary pushes ...

Read full story
Vector and Full-Text Search Explained: Why AI Agents Need Both
Key Takeaways Hybrid retrieval catches the identifiers embeddings miss and the paraphrased questions keyword search misses. Reciprocal rank fusion merges keyword and semantic results by rank, without reconciling incompatible scores. Agent retrieval depends on tenant filters, permissions, and fresh transactional data as much as on document similarity. ...

Read full story