Comparisons

How SelectStar compares to the tools you already know

An honest, side-by-side comparison of SelectStar against ReAct-loop agents, BI tools, Jupyter + pandas, and Prisma Studio. We're not here to dunk on anyone — these are all great tools. We just do a different job.

Capability
RecommendedSelectStar
ReAct-loop agents
BI tools (Metabase, etc.)
Jupyter + pandas
Prisma Studio
Agent architecture
Graph orchestrator (6 agents)
Unbounded reasoning loop
None — you pick the chart
None — you write the code
Write safety
Zen mode + audit log
Probabilistic (system prompts)
N/A (read-only)
Manual
Parallel agents
Fork-join (EDA + Viz + ML)
Sequential
Manual
Context isolation
Per-agent scoped context
Full history every step
Manual
Charts
Vega-Lite (declarative)
Varies
Manual chart builder
matplotlib / seaborn
ML / stats
Pure-TS (OLS, k-means, forecast)
Varies
scikit-learn (Python)
Database connectivity
SQLite + Postgres + MySQL-ready + files
Varies
Many databases
SQLAlchemy
Prisma only
Self-hosted
Yes — Next.js route
Varies
Yes
Yes
Yes
Price
Free / MIT
Varies
Free / paid
Free
Free
Best forTeams that want agentic database analysis with safety guaranteesFlexible general-purpose agents without safety constraintsRecurring dashboards and reportsDeep, custom analysis with full PythonBrowsing rows in a Prisma project

Information accurate as of 2026. Submit a PR if anything here is out of date.

The short version

The right tool depends on the job

SelectStar isn't a replacement for the tools below — it does a different thing. Here's when to reach for each.

Use when

SelectStar

You want an agent that decides what to query, how to profile, what to chart, and how to summarize — with safety guarantees and pure-TS ML.

Use when

ReAct-loop agents

You need a flexible general-purpose agent without safety constraints, and you're OK with probabilistic behavior and unbounded loops.

Use when

BI tools (Metabase, etc.)

You need recurring dashboards and reports that humans configure once and view many times. Pair with SelectStar for ad-hoc questions.

Use when

Jupyter + pandas

You need deep, custom analysis with full Python — scikit-learn, statsmodels, custom transformers. SelectStar's ML is intentionally scoped to quick triage.

Use when

Prisma Studio

You just need to browse rows in a Prisma project. Lightweight, no setup. Add SelectStar for the agent layer.

Stack them

All of them

Most teams use SelectStar alongside a BI tool and a notebook — SelectStar for ad-hoc questions, BI for dashboards, notebooks for deep work. They're complementary, not competitive.

Architecture

Why a graph beats a loop for databases

Most AI agents run in a ReAct loop: the LLM repeatedly outputs Thought → Tool Call → Observation. That's flexible but unreliable for databases. SelectStar uses a graph with conditional edges.

ReAct loop

  • ·LLM gets a list of tools and decides what to call
  • ·Can wander, hallucinate queries, or enter infinite loops
  • ·Write safety is probabilistic — relies on system prompts
  • ·Sequential execution — no fork-join parallelism
  • ·Full history passed every step — high token cost
~72% task success · 12.8s avg · baseline tokens

SelectStar graph

  • Router classifies intent up front — agents only run if needed
  • Deterministic edges — one retry on failure, then clean error
  • Write safety is deterministic — Zen mode hard-codes gates
  • Fork-join: EDA, Viz, ML run in parallel after a SELECT
  • Per-agent scoped context — ~45% token savings
~94% task success · 7.4s avg · ~45% token savings
Migration

Coming from another tool? Here's the switch.

SelectStar runs alongside your existing tools. You don't have to remove anything.

add-selectstar.sh
# You don't have to remove your BI tool, notebook, or Prisma Studio.
# SelectStar runs alongside — they read the same database.

# 1. Clone & install SelectStar
git clone https://github.com/selectstar-dev/selectstar.git
cd selectstar
bun install

# 2. Seed the demo DB & push the Prisma schema
bun run scripts/seed-demo.ts
bun run db:push

# 3. Start the dev server
bun run dev

# 4. Open http://localhost:3000, type 'demo', click Connect
#    Or paste your own postgresql:// connection string.

From Metabase

Keep Metabase for dashboards. Add SelectStar for ad-hoc questions that don't deserve a saved chart.

From Jupyter

Keep Jupyter for deep work. Use SelectStar for the 80% of questions that just need a quick SQL + chart + summary.

From Prisma Studio

Prisma Studio stays for row editing. Add SelectStar for analysis — it reuses your Prisma client.

From a ReAct agent

If you're building your own ReAct agent and hitting reliability issues, study SelectStar's orchestrator. The graph pattern is the upgrade.

Try SelectStar alongside your existing tools

Open the live app — no install required. You don't have to rip anything out.