wagner-niklas/Alfred

Alfred: An open-source Data Assistant for domain adoption, powered by agent skills, semantic knowledge graphs and relational data.

46
/ 100
Emerging

Built on Next.js with Vercel AI SDK, Alfred connects to Neo4j knowledge graphs and Databricks SQL through a tool-based agent architecture that executes natural language queries against explicit semantic models. The system exposes domain concepts and relationships as first-class navigable entities, enabling users to inspect how text-to-SQL decisions map to explicit knowledge engineering rather than implicit LLM inference. Extensible through pluggable skills, persistent multi-thread chat, and swappable persistence layers (default SQLite), it targets teams adopting data assistants who need transparency over the semantic layer and reasoning chain.

No Package No Dependents
Maintenance 13 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 14 / 25

How are scores calculated?

Stars

65

Forks

9

Language

TypeScript

License

MIT

Last pushed

Mar 10, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/wagner-niklas/Alfred"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.