The ledger for agentic data work.
-
Updated
Nov 18, 2026 - Python
The ledger for agentic data work.
DeepEye: An Autonomous Data Agent System
Open-source text-to-SQL engine you tune and measure on your own database
Benchmarking data agents for verifiable analytics over heterogeneous workspaces.
Context provider for data agents (MCP + REST + CLI): metrics, golden queries, and interpretation knowledge. Google Cloud native (Cloud Run + Cloud SQL), secret-zero.
1st place (Phase 1) / 4th place + Merit Award (Phase 2 final) solution for the KDD Cup 2026 Data Agents Challenge
Grader and results tracker for text-to-SQL systems: exact-match and got-the-facts grading on BIRD, Spider 1.0 and Spider 2.0-lite, with per-question results behind every published mnemiq figure
Open source AI agent framework to build the future of data operations.
The Open Context Layer for Data Agents
Deterministic CI regression testing for policy drift across model-visible tools, semantic validation, SQL compilation, database containment, and result release.
DataFlow AI is an enterprise-grade data analysis and visualization platform that empowers businesses and data professionals to make data-driven decisions faster. Leverage the power of artificial intelligence to automatically generate insights, create stunning visualizations, and interact with your data through natural language.
Trace Integrity for LLM data agents: execution contracts, trace validation, CAIT evaluation, and reusable artifacts for auditable structured-data reasoning.
Local RSS feed aggregator, NLP signal cleaning engine, and glassmorphic portal to track high-priority Inoreader signals
Local-first evaluation, regression testing, and reporting for data agents
An open practitioner framework for governing AI agents that query enterprise data.
A source-checked guide to AI data agents: architectures, implementations, semantic layers, benchmarks and production practices.
Shared vocabulary for measuring text-to-SQL and data-agent systems: grading rules, failure modes, refusal, stability, plus a published comparison dataset.
Measure data agents like you measure models — scenario question banks, entity-level P/R/F1, failure taxonomy, resumable runs
Microsoft Fabric POC: four Data Agent setups (Lakehouse, Ontology, semantic model, hybrid) benchmarked on synthetic title-insurance data
To associate your repository with the data-agents topic, visit your repo's landing page and select "manage topics."