#2 · Primary category： Vector Databases
tidb
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
Project last updated：08/29/26
GitHub Stars
40.5K
Forks
6.2K
Contributors
1.1K
License
Apache-2.0
Why we included this project
TiDB is a distributed SQL database with MySQL-compatible syntax that now includes native vector search, so teams building agent memory or RAG pipelines can keep embeddings in the same transactional store as their regular application data. VECTOR column types, HNSW indexes, and BM25 full-text search let a single query filter by metadata, run a nearest-neighbor lookup, and blend in keyword relevance without syncing data between two systems. That appeals to teams that already write MySQL-compatible SQL and want ACID transactions, horizontal scaling, and high availability for the same data their AI features read and write. The agent-memory pattern is documented with copy-paste schemas and a Python SDK, so developers who would rather not hand-roll a vector store have a clear path. It is a heavier, more operationally involved choice than a purpose-built vector store, and.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
supabase
The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
milvus
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
qdrant
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
chroma
Search infrastructure for AI
doris
Apache Doris is a real-time analytics and hybrid search database for AI agents.