databendlabs /databend
Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox. — rebuilt from scratch. Unified architecture on your S3.
★ 9,496⑂ 901👁 92⑃ 14,425● 6,332▤ 1,842
+1
Daily
9,496
stars
901
forks
92
watchers
14,425
prs
6,332
issues
1,842
releases
README
Databend
Enterprise Data Warehouse for AI Agents
one warehouse for all your data
SQL analytics, vector search, and full-text search in a single Rust warehouse on object storage: fast, elastic, and grows with your data — with sandboxed Python UDFs for agents.
☁️ Try Cloud •
🚀 Quick Start •
📈 Performance •
📖 Documentation
💡 Why Databend?
Databend is an open-source data warehouse built in Rust. Analytics, search, and agent workloads run on the same tables, so there is no second system to sync.
| | |
| :--- | :--- |
| 📊 One WarehouseSQL analytics, vector search, full-text search, auto schema evolution, transactions. | 🤖 Agent-ReadySandboxed Python UDFs for agent logic, SQL for orchestration. |
| 🏢 Enterprise ScaleFast vectorized engine, elastic compute on object storage: S3, Azure, GCS. | 🌿 BranchingGit-like data versioning. Agents experiment safely on production snapshots. |
!Databend Architecture
📈 Performance
Published results on Databend Cloud with default settings. Each page includes the SQL to reproduce it.
| Benchmark | Result |
| :--- | :--- |
| TPC-H SF100 vs. Snowflake | 1.25× faster, ~60% lower cost |
| Data ingestion vs. Snowflake | 5.15× faster, 91% lower cost |
| Vector & full-text search | 10M docs: vector p50 41 ms, full-text p50 35 ms |
| TPC-H SF1000 (1 TB) scaling | 4.1× faster on Large vs. Small warehouse |
See all benchmarks.
⚡ Quick Start
Cloud (Recommended) — Sign up, create a warehouse, and run SQL in the worksheet. Cloud guide →
Self-hosted — Run the all-in-one image and connect with BendSQL:
bash
docker run -d -p 127.0.0.1:8000:8000 datafuselabs/databend
bendsql -u root
See Docker image options and self-hosted deployment for credentials, storage, and production setup.
Your First Query
Analytics, full-text search, and vector search in one table:
sql
CREATE TABLE docs (
id INT,
content STRING,
embedding VECTOR(3),
INVERTED INDEX content_idx(content),
VECTOR INDEX embedding_idx(embedding) distance = 'cosine'
);
INSERT INTO docs VALUES
(1, 'SQL analytics for agents', [1.0, 0.0, 0.0]),
(2, 'Vector search for documents', [0.0, 1.0, 0.0]);
SELECT id, content FROM docs WHERE MATCH(content, 'analytics');
SELECT id, content FROM docs
ORDER BY COSINE_DISTANCE(embedding, [1.0, 0.0, 0.0]::VECTOR(3))
LIMIT 1;
Both queries return document 1. Learn more: Vector search · JSON & search.
🤖 Agent-Ready Architecture
Databend's Sandbox UDF enables flexible agent orchestration with a three-layer architecture:
- Control Plane: Resource scheduling, permission validation, sandbox lifecycle management
- Execution Plane (Databend): SQL orchestration, issues requests via Arrow Flight
- Compute Plane (Sandbox Workers): Isolated sandboxes running your agent logic
sql
-- Define your agent logic
CREATE FUNCTION my_agent(input STRING) RETURNS STRING
LANGUAGE python HANDLER = 'run'
AS $$
def run(input):
Your agent logic: LLM calls, tool use, reasoning...
answer = f"processed: Top issues
#17296bug: Databend Meta Log Data Overwrites Config Values17 comments · 2025-01-15#16417bug: Log Index Error in Meta Pod on Restart17 comments · 2024-09-07#12980ci: sandbox seems not work for internal stage.16 comments · 2023-09-22#7438Feature: functional dependency optimization12 comments · 2022-09-01#19101Feature: Implement HybridBitmap deserialization calculation based on RoaringFormatSpec11 comments · 2025-12-14#14462Feature: Spilled ArtTree Support For Databend10 comments · 2024-01-24#16140Feature: A columnar Geometry/Geography format9 comments · 2024-07-28#15553Feature: Temporal Aggregating Index9 comments · 2024-05-16
Discussions
#20407Databend into Apache Arrow through ADBC over the MySQL wire, using MySQL Connector/ODBC 9.4 (adbcBridge 0.1.0)1 comments · 2026-08-28#19485Benchmark: databend-common-ast vs other Rust SQL parsers on PostgreSQL workloads1 comments · 2026-02-25#19287[Enhancenent proposal] All-in-one app1 comments · 2026-01-18#19204system.query_log disappered after install v1.2.8611 comments · 2026-01-07#18971How to control table ownership5 comments · 2025-11-14#18725Some questions about the null type1 comments · 2025-09-16#18595Online demo1 comments · 2025-08-25#18459If the table is empty, perhaps we can directly truncate this table?2 comments · 2025-07-31
Latest release
v1.2.881 v1.2.881 2026-04-17What's Changed Exciting New Features ✨ feat(query): support create iceberg table with partition and properties by @TCeason in https://github.com/databendlabs/databend/pull/17812 feat(query): support alter table/database refresh cache by @TCeason in https://github.com/databendlabs/databend/pull/17841 feat(query): variant support extension types(Decimal, Binary, Date, Timestamp, Interval) by @b41sh in https://github.com/databendlabs/databend/pull/17835 feat: Add sampled trace support by @Xuanwo in https://github.com/databendlabs/databend/pull/17850 feat: unload preserve order if the