A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.
Repository Index
47,133 repositories indexed
1–16 of 16 · Most stars
GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more.
- bigquery
- duckdb
- llm
- postgresql
Python SQL Parser and Transpiler
- transpiler
- sql
- python
- parser
the portable Python dataframe library
Lightweight and extensible compatibility layer between dataframe libraries!
QuackOSM: an open-source Python and CLI tool for reading OpenStreetMap PBF files using DuckDB
The data transformation tool the open-source community deserves.
High-assurance AI data visualization IDE & analytics workbench. Natural language to charts with local ground-truth table verification.
- ai-analytics
- data-analysis
- data-visualization
- duckdb
Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.
- clickhouse
- databricks
- dremio
- mcp
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
Turn CSV, Excel, and read-only databases into verified, editable business reports.
- data-visualization
- self-hosted
- sql
- text-to-sql
Reverse ETL for the code-first data stack
- bigquery
- cli
- data-engineering
- dbt
Declarative data quality engine. Define checks in YAML, run anywhere.
- airflow
- anomaly-detection
- data-contracts
- data-quality
A detective for your data. Zero-config data quality monitoring — works with dbt, Postgres, BigQuery, Snowflake. No YAML.
- anomaly-detection
- bigquery
- cli
- data-engineering
Open, audit-grade agentic data quality framework with portable industry packs
Data ingestion engine — Singer taps to Parquet in cloud buckets