firma

You:    Here's my IBKR trade history [trades.csv]. Set up firma.
Claude: I see 47 transactions. Logging in chronological order... done.
        Syncing prices and FX history... your portfolio: $179K, +61% all-time. TSLA is 78%.

You:    My portfolio feels really volatile lately. Should I be worried?
Claude: TSLA is 74% of your equity — a 10% TSLA move is a 7% net worth move.
        Cash flow is solid at $6.4k/month saved. The volatility is market, not lifestyle.

You:    That July expense spike looks alarming.
Claude: That was $57k in TSLL — a leveraged bet, not spending.
        Strip it out: expenses flat at ~$7k/month, savings rate 47.8%.

You:    Give me a full overview with charts.
Claude: Net worth: $294k → $490k in 8 months, pulled back to $427k with TSLA's Q1 dip.
        [builds net worth trend, income vs expenses, portfolio allocation, unrealized P&L]

Why firma

• Talks to Claude natively. firma mcp install wires firma into Claude Desktop. Every command you can run in the terminal, Claude can call through MCP — log trades, sync prices, render charts, reason about your data.

• Local-first, no exceptions. Everything lives in ~/.firma/firma.db. No server, no sync, no account. Your financial data never leaves your machine.

• Multi-market, one stored currency. Track holdings across 9 markets (US, KRX, KOSDAQ, JP, HK, LSE, XETRA, NSE, TW) — plus non-stock assets like crypto, commodities, and real estate. Every value is stored in USD and displayed in the currency you pick, with historical FX rates from FRED — so a 2018 balance shows the 2018 exchange rate, not today's.

• Transactions as source of truth. No holdings table to drift out of sync. Portfolio, cost basis, and P&L are always derived live from your trade log.

• A daily brief that actually advises. get_brief doesn't just dump data — it returns a weekly stance (lean aggressive or defensive), ranked moves (deploy idle cash, derisk, rebalance, …), and a watchlist of new tickers, all computed deterministically from your holdings, cash flow, and macro signals. It also bundles macro signals, commodity prices, the dividend calendar, global macro (World Bank), and active disaster alerts (GDACS) in one call — no extra API keys needed for the global data.

• Developer-friendly. --json on every read command. Three clean verb groups: add, show, report.

Get started

Two ways to install — both work the same way once set up.

macOS Installer

Download and double-click. Node.js is bundled — nothing to install first. API keys are configured via setup dialogs (opens Finnhub + FRED in your browser, then prompts you to paste each key). Claude Desktop is connected automatically.

↓ Download firma-mac-arm64.pkg

npm

# 1. Install
npm install -g @evan-moon/firma

# 2. Set API keys (both free)
firma config set finnhub-key YOUR_KEY   # finnhub.io — prices, news, earnings
firma config set fred-key YOUR_KEY      # fred.stlouisfed.org — macro & FX history

# 3. Connect Claude Desktop
firma mcp install
# Restart Claude Desktop — firma tools will appear in the toolbar.

Drop your data into Claude. Paste a CSV, brokerage export, or plain text — Claude logs everything and syncs prices automatically.

Prefer the terminal? Every MCP tool has a matching firma command — see CLI reference.

If firma helps you track your money, please ⭐ star the repo — it's the cheapest way to help others find it.

CLI reference

--json is available on every read command. Alias: firma rm = firma delete.

Portfolio

Balance & Cash Flow

Transactions

Snapshots

Research (Finnhub)

Macro (FRED)

Global Intelligence (no API key)

Daily Brief & Actions

Claude integration (MCP)

After firma mcp install, Claude has full read/write access to your data through conversation. Two tools are available only via MCP:

get_brief is the primary entry point for any daily check-in or market question. In a single call it returns:

• Stance — a deterministic weekly verdict (aggressive / mixed / defensive / contrarian-aggressive) at the intersection of market signal and your personal capacity (runway, goal pace, idle cash)

• Moves — ranked recommendations: deploy idle cash, raise contributions, derisk, extend runway, rebalance, or play a tactical tilt — each with a quantified rationale and a drill_down pointer to the tool that explains it

• Watchlist — new-ticker candidates surfaced from peers of what you already hold

• Freshness — last-synced dates for prices and FX, so Claude knows when to sync first

• Portfolio — holdings with weights, daily P&L, total cost vs market value

• Concentration — HHI by ticker, sector, currency, country

• Movers — top winners and losers for the day

• News — recent headlines per holding

• Earnings — upcoming earnings dates with EPS estimates

• Economic calendar — high/medium-impact events for the week

• Macro — FRED snapshot (VIX, 10Y yield, credit spread, fed funds, FX impact in home currency)

• Stress & Regime — Economic Stress Index + Risk-on / Mixed / Risk-off bias

• Commodities — WTI oil, gold, copper (via FRED — no extra key)

• Dividend calendar — upcoming ex-dates and estimated income for held positions

• World macro — GDP growth, inflation, unemployment across major economies (World Bank — no extra key)

• Disaster alerts — active GDACS Orange/Red events (no extra key)

The recommendations are computed in code — analysis baked into the tool result, not improvised in prose. The show_* tools (show_concentration, show_macro, …) carry their dimension's recommendation too, so a drill-down stays consistent with the brief.

If today's snapshot is missing, get_brief records one automatically before assembling the brief, so daily history accrues even when you forget to run firma add snapshot.

show_valuation and show_world_intel are available for deeper drill-downs after reading the brief.

Prompts — type / in Claude Desktop to access guided workflows:

setup_status (called by Claude at the start of any conversation) also returns an analyst_context block — a lightweight version of the analyst persona that influences every reply without a manual prompt invocation.

Historical FX note: firma sync fx backfills daily FX rates (KRW, JPY, EUR, CNY, GBP, HKD, INR, TWD) from FRED starting at your earliest transaction date. Subsequent runs are increment-only. This means a 2018 balance in KRW uses the 2018 rate — not today's.

Architecture

Firma is a Yarn Berry monorepo with a layered, port-and-adapter design. The application layer never imports an external-API package directly — it talks to domain interfaces, and adapters implement those interfaces against specific services.

Workspace layout reflects the layers:

packages/
  domain/           ports + types + routers, no external-API dep
    domain/         market/ (Quote, StockSnapshot, Candle, news, …),
                    macro/ (series, country indicators, live FX, stress,
                    regime), event/ (world disaster events)
  external-api/     raw API clients, no firma-domain dep
    finnhub/  fred/  worldbank/  gdacs/  open-er-api/  yahoo-finance/
  adapter/          the only layer that imports both sides
    adapters/       provider registry — createMarketProviders, …
  use-case/         business logic
    portfolio/      brief/   advisor/
  shared/           cross-cutting
    db/             utils/
apps/
  cli/              mcp/   docs/

Import dependencies (A → B means "A imports B"):

apps/cli, apps/mcp
  → @firma/adapters        data-clients.ts builds providers via the registry
  → @firma/domain          commands/tools call domain clients directly
                           for simple reads (e.g. `show news`)
  → use-case packages      richer flows (portfolio sync, brief)

use-case (portfolio, brief, advisor)
  → @firma/domain          brief also composes @firma/advisor

@firma/adapters
  → @firma/domain          implements MarketDataProvider / MacroDataProvider /
                           EventDataProvider
  → external-api packages  calls the raw HTTP/RSS clients

external-api (finnhub, fred, worldbank, gdacs, open-er-api, yahoo-finance)
  → shared only            pure API clients; no domain/adapter knowledge

@firma/domain
  → shared only            the stable core; no external-api / adapter /
                           use-case / app dependency

shared (db, utils)
  → nothing                cross-cutting leaf; imported by every layer above

At runtime, data flows the opposite way:

External API → @firma/adapters → domain client → use-case → cli / mcp

Dependency rule: external-API packages have zero firma-domain knowledge; domain packages have zero external-API knowledge. @firma/adapters is the only package that imports both sides. Application code (apps/cli, apps/mcp) talks to domain clients; the one place it touches @firma/adapters is data-clients.ts, which constructs the concrete providers.

Capabilities — each domain interface declares a capability set; the router picks a provider per capability:

Why this matters: adding a data source touches no command or business-logic code. Adding KRX coverage, for example, means a new packages/external-api/naver/ raw client, a createNaverProvider(): MarketDataProvider in packages/adapter/adapters/src/, and one registration line in packages/adapter/adapters/src/registry.ts. See CONTRIBUTING.md for the full recipe.

Development

Requires Node.js 22+ and Yarn Berry.

corepack enable
yarn install

yarn dev:cli show portfolio    # CLI dev mode
yarn typecheck                 # Full type check
yarn test                      # Run unit tests

See CONTRIBUTING.md for the full architecture walkthrough and the recipe for adding a new external data provider.

Works with Herald

Firma is the financial intelligence layer of the Herald ambient voice assistant stack. When connected, Herald can:

• report your portfolio performance and net worth by voice

• answer "how much did I spend on fees this quarter?" without opening a spreadsheet

• surface market context mid-conversation alongside your own position data

Herald + Firma + Memex — ambient voice, financial intelligence, and persistent memory in one personal AI stack.

llms.txt

llms.txt is a machine-readable summary of this project for LLM agents — concise description with documentation links, following the llms.txt standard.

License

MIT © Evan Moon