DartLab

One stock code. The whole story.

DART + EDGAR filings, structured and comparable — in one line of Python.

Docs · Blog · Live Demo · Open in Colab · Open in Molab · 한국어 · Sponsor

The Problem

A public company files hundreds of pages every quarter. Revenue trends, risk warnings, management strategy, competitive position — the complete truth about a company, written by the company itself.

Nobody reads it.

Not because they don't want to. Because the same information is named differently by every company, structured differently every year, and scattered across formats designed for regulators, not readers. The same "revenue" appears as ifrs-full_Revenue, dart_Revenue, SalesRevenue, or dozens of Korean variations. The same "business overview" is titled differently in every filing.

DartLab is built on one premise: every period must be comparable, and every company must be comparable. It normalizes disclosure sections into a topic-period grid (~95% mapping rate) and standardizes XBRL accounts into canonical names (~97% mapping rate) — so you compare companies, not filing formats.

Quick Start

uv add dartlab

pip install dartlab              # core + AI (openai, gemini included)
pip install dartlab[server]      # + web server (FastAPI, MCP)
pip install dartlab[viz]         # + charts (Plotly)
pip install dartlab[all]         # everything

import dartlab

c = dartlab.Company("005930")       # Samsung Electronics

c.sections                          # every topic, every period, side by side
# shape: (41, 12) — 41 topics across 12 periods
#                     2025Q4  2024Q4  2024Q3  2023Q4  ...
# companyOverview       v       v       v       v
# businessOverview      v       v       v       v
# riskManagement        v       v       v       v

c.show("businessOverview")          # what this company actually does
c.diff("businessOverview")          # what changed since last year
c.BS                                # standardized balance sheet
c.ratios                            # financial ratios, already calculated

# Same interface, different country
us = dartlab.Company("AAPL")
us.show("business")
us.ratios

# Ask in natural language
dartlab.ask("Analyze Samsung Electronics financial health")

No API key needed. Data auto-downloads from HuggingFace on first use, then loads instantly from local cache.

What DartLab Is

One calling convention. Each engine: dartlab.engine() for the guide, dartlab.engine("axis") to run.

Layer	Engine	What it does	Entry point	Notebook
Data	Data	Pre-built HuggingFace datasets, auto-download	Company("005930")	—
L0/L1	Company	Filings + financials + structured data unified by ticker	c.show(), c.select()	01
L1	Gather	External market data (price, flow, macro, news)	dartlab.gather()	02
L1	Scan	Cross-company comparison (governance, ratios, cashflow, ...)	dartlab.scan()	03
L1	Quant	Technical & quantitative analysis (momentum/factor/pattern)	c.quant()	04
L2	Analysis	Profitability/stability/cashflow causal analysis + valuation + forecast	c.analysis("financial", "수익성")	05
L2	Macro	Market-level macro (cycle/rates/liquidity/sentiment/assets)	dartlab.macro("사이클")	06
L2	Credit	Independent credit rating (dCR grade, default probability, health)	c.credit("등급")	07
L2	Review	Composes analysis engines into a report (rich/html/markdown/json)	c.review("수익성")	08
L3	AI	Active analyst — code execution + interpretation	dartlab.ask()	09
L4	Channel	External sharing — dartlab channel brings PC dartlab to your phone	dartlab channel	—
core	Search	Semantic filing search (alpha)	dartlab.search()	10
facade	Listing	Catalog API (companies, filings, topics)	dartlab.listing()	11
viz	Viz	Charts and diagrams (emit_chart)	emit_chart({...})	—
guide	Guide	Concierge — readiness, error handling, education	dartlab.guide.checkReady()	—

All notebooks: marimo · colab ·

Company

Design: ops/company.md

Three data sources — docs (full-text disclosures), finance (XBRL statements), report (DART API) — merged into one object. Data auto-downloads from HuggingFace, no setup needed.

c = dartlab.Company("005930")

c.index                         # what's available -- topic list + periods
c.show("BS")                    # view data -- DataFrame per topic
c.select("IS", ["매출액"])       # extract data -- finance or docs, same pattern
c.trace("BS")                   # where it came from -- source provenance
c.diff()                        # what changed -- text changes across periods

Scan — Cross-Company Comparison

Design: ops/scan.md

Cross-company analysis across all listed firms. Governance, workforce, capital, debt, cashflow, audit, insider, quality, liquidity, network, account/ratio comparison, and more.

dartlab.scan("governance")            # governance across all firms
dartlab.scan("ratio", "roe")          # ROE across all firms
dartlab.scan("cashflow")              # OCF/ICF/FCF + 8-pattern classification

Gather — External Market Data

Design: ops/gather.md

Price, flow, macro, news — all as Polars DataFrames.

dartlab.gather("price", "005930")             # KR OHLCV
dartlab.gather("price", "AAPL", market="US")  # US stock
dartlab.gather("macro", "FEDFUNDS")           # auto-detects US
dartlab.gather("news", "삼성전자")             # Google News RSS

Analysis — 14-Axis Financial Analysis

Design: ops/analysis.md

Revenue structure → profitability → growth → stability → cash flow → capital allocation → valuation → forecast. Turns raw statements into a causal narrative that feeds Review, AI, and direct human reading.

c.analysis("financial", "수익성")       # profitability analysis
c.analysis("financial", "현금흐름")    # cash flow analysis

print(c.credit())                           # available-axes guide DataFrame (self-discovery)
c.credit("등급")                            # dCR-AA, healthScore 93/100
c.credit("등급", detail=True)               # grade + narrative + metrics

Credit — Independent Credit Rating

Design: ops/credit.md | Reports: dartlab.pages.dev/blog/credit-reports

Independent credit analysis with 3-Track model (general/financial/holding), Notch Adjustment, CHS market correction, and separate financial statement blending.

79-company validation: large-cap 87% (26/30), mid-cap 82% (41/50), full sample 70% (55/79, re-measurement pending after v5.0 overvaluation fix). Samsung AA+ exact match. See methodology for validation details.

print(c.credit())           # self-discovery — available axes + grade

cr = c.credit("등급")        # main grade
print(cr["grade"])          # dCR-AA+
print(cr["healthScore"])    # 96 (0-100, higher is better)
print(cr["pdEstimate"])     # 0.01% default probability

cr = c.credit("등급", detail=True)  # grade + narrative + metrics + divergence explanation
print(cr["divergenceExplanation"])  # why it differs from agencies

Publish reports (credit narrative + audit are auto-included in review's 5막):

from dartlab.review.publisher import publishReport
publishReport("005930")               # 6막 report including credit narrative + audit

Review — Analysis to Report

Design: ops/review.md

Assembles analysis into a structured report. 4 output formats: rich (terminal), html, markdown, json.

c.review()              # full report
c.reviewer()            # report + AI interpretation

Sample reports: Samsung Electronics · SK Hynix · Kia · HD Hyundai Heavy Industries · SK Telecom · LG Chem · NCSoft · Amorepacific

Search — Find Filings by Meaning (alpha)

Design: ops/search.md

No model, no GPU, no cold start. 95% precision on 4M documents — better than neural embeddings at 1/100th the cost. See methodology for benchmark details.

dartlab.search("유상증자 결정")                     # find capital raise filings
dartlab.search("대표이사 변경", corp="005930")       # filter by company
dartlab.search("회사가 돈을 빌렸다")                 # natural language works too

AI — Active Analyst

Design: ops/ai.md

The AI writes and executes Python code using dartlab's full API. You see every line of code it runs. 60+ questions validated, 95%+ first-try success. See methodology for validation scope and limits.

dartlab.ask("Analyze Samsung Electronics financial health")
dartlab.ask("Samsung analysis", provider="gemini")  # free providers available

Providers: gemini (free), groq (free), cerebras (free), oauth-codex (ChatGPT subscription), openai, ollama (local), and more. Auto-fallback across providers when rate-limited.

Channel — Use your PC dartlab from anywhere

Design: ops/channel.md

One command on your PC and dartlab UI works on your phone. Microsoft DevTunnels auto-setup.

dartlab channel

Flow:

1. winget auto-installs the devtunnel CLI (one-time)
2. GitHub OAuth (one-time, browser opens automatically)
3. Permanent URL + QR code (https://<id>-8400.<region>.devtunnels.ms)
4. Open the URL/QR on your phone Chrome → dartlab UI just works

Zero domains, zero token tricks. Same infrastructure as VS Code Remote Tunnels — verified mobile compatibility. Optional messaging bots: --telegram/slack/discord.

Architecture

L0  core/        Protocols, finance utils, docs utils, registry
L1  providers/   Country-specific data (DART, EDGAR, EDINET)
    gather/      External market data (Naver, Yahoo, FRED)
    scan/        Market-wide analysis — scan("group", "axis")
L2  analysis/    Financial + forecast + valuation + quant — analysis("group", "axis")
    credit/      Independent credit rating — c.credit()
    macro/       Market-level macro — dartlab.macro()
    review/      Block composition (analysis + credit)
L3  ai/          Active analyst — dartlab.ask()
L4  vscode/      VSCode extension (dartlab chat --stdio)

Import direction enforced by CI. Adding a new country means one provider package — zero core changes.

Layer consumption flow

Who consumes whom across the stack:

flowchart TB
    subgraph L4["L4 · User interface"]
        UI["vscode / CLI / web"]
    end
    subgraph L3["L3 · LLM analyst"]
        AI["ai<br/>dartlab.ask()"]
    end
    subgraph L2["L2 · Analysis"]
        ANA["analysis<br/>causal financial + forecast + valuation"]
        CRD["credit<br/>independent rating"]
        MAC["macro<br/>market reading"]
        REV["review<br/>block-composed report"]
    end
    subgraph L1["L1 · Data ingestion"]
        PRV["providers<br/>DART / EDGAR / EDINET"]
        GAT["gather<br/>FRED / ECOS / Naver / Yahoo"]
        SCN["scan<br/>cross-market"]
        QNT["quant<br/>25 technical indicators"]
    end
    subgraph L0["L0 · Infrastructure"]
        CORE["core<br/>protocols + finance + docs + search"]
    end

    UI --> AI
    AI --> REV
    AI --> ANA
    AI --> MAC
    AI --> SCN
    REV --> ANA
    REV --> CRD
    ANA --> PRV
    ANA --> GAT
    CRD --> PRV
    MAC --> GAT
    SCN --> PRV
    QNT --> GAT
    PRV --> CORE
    GAT --> CORE
    SCN --> CORE
    QNT --> CORE

    classDef l0 fill:#f5f5f5,stroke:#999
    classDef l1 fill:#e8f4ff,stroke:#4a90e2
    classDef l2 fill:#fff4e6,stroke:#e67e22
    classDef l3 fill:#f0e6ff,stroke:#8e44ad
    classDef l4 fill:#e6ffe6,stroke:#27ae60
    class CORE l0
    class PRV,GAT,SCN,QNT l1
    class ANA,CRD,MAC,REV l2
    class AI l3
    class UI l4

Loading

Core rules:

• Arrows always flow top → bottom (L4→L3→L2→L1→L0). Reverse imports forbidden (CI-enforced)
• L2 engines never import each other — analysis ↛ credit, macro ↛ analysis. Composition is review's or ai's job
• When adding a feature, pick the right layer first and let data flow in one direction only

EDGAR (US)

Same interface, different data source. Auto-fetched from SEC API — no pre-download needed.

# Korea (DART)                          # US (EDGAR)
c = dartlab.Company("005930")           c = dartlab.Company("AAPL")
c.sections                              c.sections
c.show("businessOverview")              c.show("business")
c.BS                                    c.BS
c.ratios                                c.ratios
c.diff("businessOverview")              c.diff("10-K::item7Mdna")

Macro — Economy Without a Ticker

Design: ops/macro.md

No Company needed. Read the economy with import dartlab.

dartlab.macro("사이클")          # Business cycle — 4 phases
dartlab.macro("금리")            # Rates + Nelson-Siegel yield curve
dartlab.macro("예측")            # LEI + Cleveland Fed probit + Hamilton RS + GDP Nowcast
dartlab.macro("위기")            # Credit-to-GDP gap + Minsky + Koo + Fisher
dartlab.macro("기업집계")        # Bottom-up: earnings cycle, Ponzi ratio, leverage
dartlab.macro("종합")            # Macro summary + investment strategies + portfolio allocation

# Scenario
dartlab.macro("사이클", overrides={"hy_spread": 600})

# Backtest
dartlab.macro("금리", as_of="2022-01-01")

Cycle, rates, assets, sentiment, liquidity, forecast, crisis, inventory, corporate, trade signals — global macro methods (Hamilton EM, Kalman DFM, Nelson-Siegel, Cleveland Fed probit, Sahm Rule, BIS Credit-to-GDP, GHS, Minsky, Koo, Fisher, Cu/Au, FCI) implemented in numpy only (zero statsmodels/scipy).

Backtest result (2000-2024, FRED): Cleveland Fed probit detected 3/3 US recessions with 2-16 month lead time, recall 90% at threshold 0.20.

MCP — AI Assistant Integration

Built-in MCP server for Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.

# Claude Code — one line setup
claude mcp add dartlab -- uv run dartlab mcp

# Codex CLI
codex mcp add dartlab -- uv run dartlab mcp

Claude Desktop / Cursor config

Add to claude_desktop_config.json or .cursor/mcp.json:

{
  "mcpServers": {
    "dartlab": {
      "command": "uv",
      "args": ["run", "dartlab", "mcp"]
    }
  }
}

Or auto-generate: dartlab mcp --config claude-desktop

OpenAPI — Raw Public APIs

from dartlab import OpenDart, OpenEdgar

# Korea (requires free API key from opendart.fss.or.kr)
d = OpenDart()
d.filings("삼성전자", "2024")
d.finstate("삼성전자", 2024)

# US (no API key needed)
e = OpenEdgar()
e.filings("AAPL", forms=["10-K", "10-Q"])

Data

All data is pre-built on HuggingFace — auto-downloads on first use. EDGAR data comes directly from the SEC API.

Dataset	Coverage	Size
DART docs	2,500+ companies	~8 GB
DART finance	2,700+ companies	~600 MB
DART report	2,700+ companies	~320 MB
EDGAR	On-demand	SEC API

Pipeline: local cache (instant) → HuggingFace (auto-download) → DART API (with your key). Most users never leave the first two.

Try It Now

Live Demo — no install, no Python

Notebooks: Company · Scan · Review · Gather · Analysis · Ask (AI)

Documentation

Docs · Quick Start · API Overview · Blog (120+ articles)

Stability

Tier	Scope
Stable	DART Company (sections, show, trace, diff, BS/IS/CF, CIS, index, filings, profile), EDGAR Company core, valuation, forecast, simulation
Beta	EDGAR power-user (SCE, notes, freq, coverage), credit, insights, distress, ratios, timeseries, network, governance, workforce, capital, debt, chart/table/text tools, ask/chat, OpenDart, OpenEdgar, Server API, MCP
Experimental	AI tool calling, export, viz (charts)

See docs/stability.md.

Contributing

Contributors are very welcome. Whether it's a bug report, a new analysis axis, a mapping fix, or a documentation improvement — every contribution makes dartlab better for everyone.

The one rule: experiment first, engine second. Validate your idea in experiments/ before changing the engine. This keeps the core stable while making it easy to try bold ideas.

• Experiment folder: experiments/XXX_name/ — each file must be independently runnable with actual results in its docstring
• Data contributions (e.g. accountMappings.json, sectionMappings.json): accepted when backed by experiment evidence
• Issues and PRs in Korean or English are both welcome
• Not sure where to start? Open an issue — we'll help you find the right place

License

MIT