Back to browse
GitHub Repository

Dex is the agent-native analytics engineering toolkit. Point it at your warehouse and your dbt project. It learns the landscape, authors your transformations, and tells you exactly what to fix when the schema drifts. Built for analytics engineers and data engineers who want more out of their coding agent.

13 starsPython

Dex – Explore any Data Warehouse without worrying about costs

by marcociavarella·Jul 22, 2026·3 points·0 comments

AI Analysis

●●●BangerSolve My ProblemBig Brain

Closes the context gap for coding agents by owning the dbt project as a first-class object.

Strengths
  • Read-only warehouse exploration with PII-aware query firewalls prevents costly mistakes.
  • Explicitly handles schema drift and semantic model coherence over time.
  • Integrates directly into Claude Code and generic agents via standardized skills.
Weaknesses
  • Heavily dependent on the dbt ecosystem, limiting utility for non-dbt users.
  • Agent reliability depends on underlying LLM performance for complex SQL generation.
Category
Target Audience

Analytics engineers, data engineers

Similar To

dbt Cloud · Metabase · Datafold

Similar Projects

AI/ML●●Solid

Dex – Cost-aware analytics engineering skills for agents

Cost guardrails for Snowflake queries when agents token-max and burn your budget.

Niche GemSolve My Problem
marcociavarella
5013d ago
DataPass

OpenSustain.Analytics

Clickable project and organisation pages plus CSV downloads make this an immediately usable explorer for anyone auditing open-source climate work. The dashboard surfaces rankings, timelines and 'Good First Issues' links (via ClimateTriage), which is practical; however citation coverage is thin and there's limited methodological detail, so it feels like a strong MVP rather than a breakthrough.

Niche GemShip It
protontypes
105mo ago
AI/ML●●Solid

Claw Diary – Show HN: Visualize what your AI agent does every day

If you run personal agents this nails a frequently ignored need: it auto-collects agent lifecycle events via Claude hooks and turns raw calls into readable daily markdown, searchable timelines with animated replay, and 30-day cost/failure analytics. The local-only model and the whimsical 'AI Journal' entries are neat differentiators — main caveat: it’s tightly coupled to Claude hooks and the install/edit-settings friction will limit casual adoption.

Niche GemShip It
agentguard
105mo ago
AI/ML●●Solid

DecisionBox – Autonomous AI agent runs data discovery on your warehouse

Every insight re-queried before shipping — catches hallucinations early.

Big BrainBold Bet
seltug
603mo ago