Seshat BI

From messy retail data to trusted Power BI -- with evidence at every gate.

An agent-first readiness system that profiles sources, governs mappings, validates the medallion warehouse, binds metrics to contracts, and prepares Power BI delivery without skipping the human decisions that make analytics trustworthy.

_{Fund open-source work on validation, compatibility, documentation, and agent safety.}

Run the demo  ·  Start contributing  ·  Sponsor a roadmap lane

Trust is a workflow, not a dashboard theme

A dashboard can look finished while its metrics are undefined, its source assumptions are unsafe, and its totals have never been reconciled. Seshat BI makes those gaps visible before they become executive decisions.

It answers one question:

Is this retail source ready to become trusted Power BI?

The answer is never a made-up score. Readiness is recorded as status + evidence + blocking_reasons, with named human approvals for judgment calls such as grain, PII, business rollups, and publish safety.

Named for the ancient Egyptian figure of writing, measurement, and record keeping, Seshat brings the same discipline to modern analytics: map meaning, record evidence, then build.

Seven gates between raw data and publication

Each stage can begin only after the prior stage passes. The sequence is the product.

flowchart LR
    S1[1. Source] --> S2[2. Mapping] --> S3[3. Silver] --> S4[4. Gold]
    S4 --> S5[5. Semantic Model] --> S6[6. Dashboard] --> S7[7. Publish]

    classDef stage fill:#001E35,stroke:#C69214,stroke-width:1.5px,color:#F7F1E7;
    class S1,S2,S3,S4,S5,S6,S7 stage;

[!IMPORTANT] Seshat never self-grants an approval, invents source meaning, or turns a green static check into a claim of live semantic correctness.

See it work

Try the bundled synthetic retail fixture. It needs no database and no Power BI Desktop:

pipx install seshat-bi
seshat demo init
seshat demo run
seshat demo report --format html

The self-contained report shows evidence, blockers, approvals, and the next allowed action across all seven stages. Offline proof stops honestly at Gold Ready; advancing farther requires a live database boundary and governed downstream artifacts.

Why teams choose Seshat BI

This makes Seshat useful to BI developers, analytics engineers, data engineers, analytics leaders, and teams building agents that must stay truthful around real business data.

How it works

flowchart LR
    RAW([Retail source]) --> B[(bronze)] --> S[(silver)] --> G[(gold)] --> PBI[Power BI PBIP]
    MAP{{Source map}} -. clears .-> S
    CHECK{{seshat check}} -. static gates .-> S
    CHECK -. static gates .-> G
    LIVE{{seshat validate}} -. live boundary .-> G
    CONTRACT{{Metric contracts}} -. govern measures .-> PBI
    HUMAN([Named human approvals]) -. authorize decisions .-> MAP
    HUMAN -. authorize publication .-> PBI

The agent is the interface. seshat check and seshat validate are gates the agent calls; they are helpers, not the product experience.

Choose your path

What is built today

Seshat BI is an active beta on PyPI -- the PyPI badge above carries the current release. The shipped system includes:

• Static and live governance gates over SQL, TMDL/PBIR, DAX, configuration, documentation, keys, date coverage, orphan relationships, and reconciliation.
• Seven-stage agent control surfaces through seshat status and seshat next, grounded in committed evidence rather than a separate run-state engine.
• Governed source mapping and metric contracts that stop transformation or dashboard work when business meaning is unresolved.
• DAX governance and generation through static rules, contract-drift checks, live value proxies, and verified measure generation.
• Portable proof surfaces including offline HTML, review JSON, SARIF, a GitHub Action, readiness passports, and an offline portfolio explorer.
• A read-only MCP governor that exposes governance state while refusing execution and approval by construction.
• Governed extension packs plus optional dbt and Dagster adapters that remain advisory and never create readiness truth.
• Source-controlled Power BI workflows with deterministic PBIR authoring helpers and a read-only assessment path for existing PBIP projects.
• Seshat Studio, a local analyst console (seshat-studio, [studio] extra) whose browser views show workspace readiness, per-table journeys and the agent conversation over the same committed evidence. Operations, run history and client review ship as API endpoints without browser views today. Studio surfaces the gates and never grants an approval of its own.

Explore the capability inventory, release history, and roadmap for the evidence behind each claim.

[!WARNING] Power BI writes are gated, not free. The governed local write leg (F016 slice 5, seshat pbi-mcp plan-write / apply) ships and refuses to act without an approved, in-scope target; the remote leg remains deferred and owner-gated. Building the final approved page in Power BI Desktop remains a named human action. See ADR 0018 for what was unparked and what was not.

Install

Python CLI

# core CLI (static checks + the offline demo)
pipx install seshat-bi
seshat init-project my-bi

# to also run the live-data steps (`seshat validate`, `seshat drift`), add the
# optional Postgres driver. Either install it inline:
pipx install "seshat-bi[db]"
# or inject it into an existing pipx install:
pipx inject seshat-bi psycopg2-binary

# governed statistical evidence (exact-pinned numerical environment)
pipx install "seshat-bi[stats]"
seshat analyze --help

The seshat command is primary. retail is a deprecated compatibility alias kept for one deprecation cycle. Live database validation needs the optional db extra (shown above) and a DSN stored only in a gitignored .env. If the driver is missing, seshat validate / seshat drift print the exact pipx inject / pip install remedy rather than a raw import error.

The studio extra installs the local analyst console's web stack (FastAPI and Uvicorn); a base install stays free of them, and seshat-studio reports the extra's absence as a named diagnostic rather than an import traceback.

The stats extra enables governed descriptive, inference, correlation, regression, anomaly, and forecast evidence. Change-point detection additionally uses the stats-change extra. The Gold statistical provider is read-only and initially PostgreSQL-only; offline local CSV evidence needs no database. See the architecture boundary and synthetic workflow.

Claude Code plugin

/plugin marketplace add Kemetra/Seshat-BI
/plugin install seshat-bi@seshat-bi-marketplace

Codex plugin

codex plugin marketplace add https://github.com/Kemetra/Seshat-BI
codex plugin add seshat-bi@seshat-bi-repository

Detailed setup: user install | agent install | support matrix

Contributing

You do not need to learn the whole readiness system before making a useful first contribution. Seshat provides bounded lanes with owned files, forbidden scope, acceptance evidence, and exact verification commands.

1. Read the first-contribution guide.
2. Pick one lane from contribution-lanes.yaml.
3. Claim a starter contribution.
4. Follow the setup and pull-request checks in CONTRIBUTING.md.

Contributions are especially welcome in governance rules, database compatibility, synthetic fixtures, documentation, Power BI artifacts, and agent workflows.

Sponsor Seshat BI

Trusted BI infrastructure is public-interest work: the rules, examples, tests, and documentation should remain inspectable by the teams that depend on them. Sponsorship can accelerate public, evidence-backed roadmap lanes such as:

• database compatibility and live-validation evidence,
• reproducible demo fixtures and cross-engine coverage,
• documentation, onboarding, accessibility, and contributor support,
• agent-safety research around analytics approvals and disclosure boundaries.

The guardrail is simple: funding supports the work; it never buys a readiness approval, a rule exception, or an undisclosed product claim.

Sponsor Seshat BI through GitHub Sponsors  ·  Discuss a public roadmap sponsorship

For organization-level sponsorships or roadmap discussions, use the issue link only for non-confidential context. Do not post procurement, client, or payment information in a public issue.

Repository guide

Essential documentation

Deliberate boundaries

Seshat BI is a governed Retail BI factory, not a one-click dashboard generator, a Fabric deployment platform, a universal ERP connector, or an automated approval engine. New automation is valuable only when it strengthens one readiness stage without taking a decision away from its accountable human owner.

License

Seshat BI is available under the Apache License 2.0.