AgentIndex icon
AgentIndex
dst logo
dst
★ 16
vs
publisher logo
publisher
★ 118

dst vs publisher

dst: dst (data serve tool) is an open-source semantic layer and MCP server that connects AI tools like Claude, ChatGPT, and Copilot to your data warehouse, ensuring data accuracy and governance. It provides a controlled interface for AI to answer plain language questions with grounded numbers, SQL, confidence grades, and attached receipts, bringing engineering best practices to the data-to-AI lifecycle.; publisher: Malloy Publisher is an analytics engine for Malloy, designed to serve data models to AI agents, applications, and BI tools. It unifies data modeling, query, materialization, access control, and API into a single server, streamlining the data stack for the AI era.

01

TL;DR

dst logo
dstRAG / Knowledge Base · ★ 16

Providing accurate and governed data answers to conversational AI agents (e.g., ChatGPT, Claude) from enterprise data warehouses.

Read dst full review →
publisher logo
publisherRAG / Knowledge Base · ★ 118

Automated data model creation from diverse sources using AI.

Read publisher full review →
02

Side-by-Side Comparison

Field
dst logodst
publisher logopublisher
Category
RAG / Knowledge Base
RAG / Knowledge Base
Stars
★ 16
★ 118
License
Apache-2.0
MIT
Install Command
pip install dst-core && dst init analytics --warehouse demo --yes && cd analytics && dst dev
npx @malloy-publisher/server@latest --port 4000
Updated
1d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
Semantic Layer, Data Governance, AI Data Integration
Analytics Engine, Data Modeling, AI Agent Integration
03

Features

dst logodst
01Governed Semantic Layer: Provides a single, controlled interface between AI and data warehouses, ensuring AI answers are based on defined business logic.
02Automated Data Testing & Validation: Every approved answer becomes a regression test, running on every deploy to prevent silent data inaccuracies.
03Transparent Data Answers with Receipts: Every AI-generated data answer includes the producing SQL, confidence, and a verifiable receipt, enhancing trust and auditability.
04Engineering Best Practices for Data Serving: Incorporates software engineering principles like version control, CI/CD, and audit trails for managing data serving to AI.
05Typed Serving & Clarification: Instead of guessing, dst uses typed decisions to compile SQL and can ask for clarification when a word is ambiguous.
publisher logopublisher
01AI Agent-driven Data Modeling
02Unified Analytics for AI Agents and BI Tools
03Declarative Dashboards and HTML Data Apps
04Robust Data Governance and Access Control
05Query Optimization via Materialization
04

Use Cases

dst logodst
↳Providing accurate and governed data answers to conversational AI agents (e.g., ChatGPT, Claude) from enterprise data warehouses.
↳Preventing AI models from generating incorrect or speculative data analysis by grounding their responses in defined business logic and validated SQL.
↳Implementing a robust data governance framework for AI applications, ensuring all data access and interpretation are auditable and compliant.
↳Automating regression testing for data definitions and metrics, ensuring that changes to the semantic layer do not silently break existing data interpretations.
↳Developing internal AI agents or copilots that require reliable and verifiable access to an organization's analytical data.
publisher logopublisher
↳Automated data model creation from diverse sources using AI.
↳Enabling natural language querying for AI agents and BI users.
↳Developing and deploying interactive data dashboards and applications.
↳Securing data access with fine-grained governance rules.
↳Accelerating analytical queries through persistent materialization.
FAQ

FAQ

What is the difference between dst and publisher?
Both dst and publisher are in the RAG / Knowledge Base category. dst has 16 stars, while publisher has 118 stars.
Which is better, dst or publisher?
The best choice depends on your use case. Choose dst if Providing accurate and governed data answers to conversational AI agents (e.g., ChatGPT, Claude) from enterprise data warehouses., and publisher if Automated data model creation from diverse sources using AI..
Is dst free or open source?
Yes, dst is open source on GitHub (Apache-2.0).
Is publisher free or open source?
Yes, publisher is open source on GitHub (MIT).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to dst →Alternatives to publisher →dst details →publisher details →