Connect your books.Ask your AI.
Sync QuickBooks into a graph Claude, ChatGPT, or any MCP client can reason over. Statements that tie, a plan that rolls off your actuals, and your numbers beside public companies. One company or a whole group: each keeps its own books and close, and your AI drafts the consolidation. Nothing writes back until you post an entry.
Nothing reaches QuickBooks until you post an entry. Read, analyze and plan first.
Eliminations, an outside owner's share and equity-method companies, drafted from each company's own books.
Click a number on a statement or report and see the accounts it was summed from, down to the register.
Your board pack is out of date the day you send it
An export keeps the numbers and loses everything behind them. Keep the books on a ledger your AI can query, and the answer is current and you can ask why.
Start with the answers. The close comes last.
Reading your books writes nothing back, so you can put RoboLedger to work on questions today and hand it the close once you trust it.
Connect your books
Link QuickBooks with one-click OAuth, then add one MCP address to Claude, ChatGPT, or any MCP client and sign in. For a group, add each company with the share the parent holds, with a bank feed and an opening balance sheet.
Ask, share, plan
Ask why a number moved and open it down to the account register. Send the board a statement that ties, roll a plan forward from your actuals, and add the SEC filings beside your books to see where you stand against public companies.
Approve the close
Bank lines arrive with a suggested account, schedules draft their entries, and the close waits on the reconciliations you choose. For a group, your AI then drafts the consolidating entries and the group close posts them. Nothing writes back to QuickBooks until you post an entry.
From the first question to the close
Seven views of the same live books. Read the statements, for one company or a whole group, open any number, plan forward, and ask in plain English. When you trust it, the close and the inbox are there too.
Live statements, and every figure opens
See the balance sheet and income statement straight from the ledger on any day of the month, no close required, for one company or the whole group. Click a figure to see the accounts it was summed from. When it is time to send, generate a validated report package.
- Drill from a statement, the trial balance or the journal into an account's register
- Income statement columns by department, class, location or project, and CSV on every statement
- Tavi and XBRL 2.1 report packages, shared with your board, lenders and investors through publish lists
Consolidated statements, drafted from each company's books
Add each company with the share the parent holds. Every month your AI drafts the consolidating entries from the books: the parent's investment against each subsidiary's capital, what the companies owe and bill each other, and an outside owner's share. A person posts them, and the group's month closes only when it all ties.
- A worksheet with every company in its own column, then combined, the adjustments and consolidated
- Noncontrolling interest, the equity method, and a company bought, partly sold or sold out of the group mid-year
- Each company closes on its own calendar; what the books cannot explain is named for you, never plugged
Open up any number and see how it was built
When someone asks where a number came from, open it. Every statement, schedule, metric, and disclosure is an Information Block, and the Explorer renders any of them through the same view projections, so the rendered figure and the facts behind it are one toggle apart.
- Six views per block: rendered, chart, facts, elements, validation, and business rules
- Compute a metric for a new period on the spot and watch its time series extend
- Deep-linkable state (?block= / ?view= / ?scenario=) and CSV export on every view
Plan forward from the books you just closed
Your closed months and your forecast in one monthly grid. Switch to a scenario and see what it does to cash, with its levers sitting right beneath the statements they drive.
- Income Statement, Balance Sheet, and Cash Flow month by month, with actuals and forward columns in the same row
- Switch scenarios in place; the assumption levers driving the forecast render in the same grid
- Trailing-window control, CSV export, and shareable scenario links
Ask about your books, or have it do the work
Get the answer yourself instead of waiting on a report, and hand off the routine work. Use the AI Console in the app, or connect Claude, ChatGPT, or any MCP client and use the same tools from the chat you already use.
- Ask in plain English; answers come from your ledger, with the generated query beside the result
- Start with /do to sort bank-feed lines, draft the month’s schedule entries, or build a metric, forecast, or draft report, on a stronger model than questions use, because a wrong change costs more than a wrong answer
- Nothing posts on its own: what it sorts or drafts waits for a person to commit, close, or file
Close the period with guard rails
The entries get drafted; you review and approve. A sequential close backed by a fiscal calendar, reconciliations and a rule engine, so no one locks an unbalanced, unreconciled or out-of-order month.
- Bank reconciliations against the statement: its cycle, the lines the bank has not cleared, the roll-forward, and a sign-off
- Schedules for depreciation, prepaids, loans and custom curves, previewed month by month before they draft
- Blockers in plain words (sync stale, out of sequence, unmapped accounts), reopen with an audit reason, optional write-back to QuickBooks
An inbox for your books
Every QuickBooks transaction and bank line lands as a typed business event: captured, classified, then committed. Bank lines arrive with a suggested account and where it came from; you set the rules, and nothing posts without a decision.
- Suggestions from the counterparty's learned default, the bank's category or AI, each labelled, and the learned ones approved in bulk
- Posting Rules: a rule your AI proposes books nothing until a person approves it
- Settle a bill from the line it paid, and see receivables and payables aged by days past due
Your agent has the wider surface
Every write operation on the platform becomes an MCP tool the day it ships. Screens follow where they earn it, so there are things your AI assistant can do today that don't have a button yet.
One connector per set of books, side by side in the same chat. A group's companies share one; each client gets its own. Your AI reads each one and answers across all of them.
Author a forecast scenario
Name the scenario, set the horizon and base period, assert the driver levers, then derive the forward slice. The Plan grid picks it up on the next load.
Define a new metric
Declare a metric block and its operands once; the Block Explorer computes and charts its standing time series from then on.
Write an event-handler rule
Teach the ledger how a new kind of business event should post. The rule your AI writes waits in Posting Rules, booking nothing until a person approves it there.
Push an approved entry back out
Publish a committed event to the source-of-truth system, and manage the obligations and schedules that feed the close.
Compare across companies
Build a fact grid over canonical concepts to line your numbers up against SEC filers on the same taxonomy.
Run the graph itself
Rebuild the analytical graph after a batch of writes, take a backup, or stand up an isolated workspace to try something out.
Add this address as a connector in Claude, ChatGPT, or any MCP client, sign in, and choose the books. One connector covers a whole group; add it again for each client you look after. It can read your books and drive these tools directly, with you approving each write. No install, no key to paste. The same tools back the in-app AI Console, so nothing is locked behind a desktop app.
https://api.robosystems.ai/v1/mcpPowered by RoboSystems
Your numbers live in a financial knowledge graph: a unified three-block model of taxonomy, events, and information. Every figure is traceable to its source, queryable in plain English, and validated before it's filed, for one company or a whole group.
Data Sources
- • Chart of accounts
- • Journal entries
- • Transaction data
- • 10-K/10-Q filings
- • XBRL standards
- • Taxonomy data
- • Direct bank & card transactions
- • Account balances
Three-Block Model
Applications
Accounting and financial reporting
Ask, plan, and close from Claude, ChatGPT, or any MCP client
Python, TypeScript, and REST clients
Automated Sync
Keep connected sources in step with your ledger — sync on demand or on a schedule
Unified Data Model
Single source of truth connecting accounting, reporting, and regulatory data
Graph Database Performance
Fast, interactive queries on complex accounting relationships powered by knowledge graph technology
Open by default
RoboLedger is open source and built so you're never trapped.
Open source
Apache-2.0. Inspect every line — see exactly how each number is produced.
You own your data
Your books, your graph. Nothing locked in a vendor black box.
No lock-in
Fork it and take it in-house whenever you want.
Your people run it. Harbinger trains them.
Harbinger FinLab implements RoboLedger and trains the people who’ll work in it every day: your own accountant, or the fractional CFO or bookkeeper you work with, and their staff. They work from the AI chat they already use. AI drafts, they approve, and they do every step. It starts with a live demo, at no cost.
Meet Harbinger FinLabRun RoboLedger across your whole client book. We walk you through the first client on a screenshare and train your staff; your clients stay yours.
Your people set up RoboLedger with us on a screenshare, then we train them to run it. No controller yet? We’ll point you to a practice that runs RoboLedger.
Each company keeps its own books on RoboLedger, run by its own accountant, and its filed reports land in your graph as data, not PDFs. The investor side is early, and we say so.
Harbinger runs its own month-end close on RoboLedger, and so does RoboSystems. We train the workflow because we work in it every month.
Nobody from Harbinger posts, approves or closes a period on your books, or signs in to them. Sign-off is yours, by name.
Questions, answered
The things finance teams ask before they connect their books.
Can it consolidate a group of companies?
Yes. A holding company and its LLCs, a franchise operator, a founder with three companies: each company keeps its own books, chart and close, and the group is built from shared reporting concepts, never from account names. Every month your AI drafts the consolidating entries (the parent's investment against each subsidiary's capital, what the companies owe and bill each other, an outside owner's share) and a person posts them. Equity-method companies, acquisitions, changes in ownership and a company sold out of the group are handled too. Not yet: companies in another currency, or a group inside a group. How consolidation works
Do I have to leave QuickBooks?
No. RoboLedger syncs the group parent's QuickBooks chart of accounts and transactions. The other companies start from their opening balance sheet and come in through a bank feed, the API or a file. Reading, analysis, and planning write nothing back; approved entries go back to QuickBooks only when you post them.
Where does my financial data live?
In your own knowledge graph on the RoboSystems platform. RoboLedger is open source, so you can inspect exactly how every number is produced, and you can fork it and take it in-house whenever you want.
Do I need to know XBRL or US-GAAP?
No. AI Auto-Map proposes the US-GAAP mapping for each company's chart of accounts with confidence scores, and the rule engine validates every entry before you lock a period. You review and adjust, and you can add, rename, move or retire accounts in the app. The taxonomy work happens for you.
What does the AI actually do?
It answers questions about your books in plain English, opens any number down to the facts behind it, rolls plans forward, and compares you to public companies. When you're ready, it also sorts bank lines into accounts, drafts the month's schedule entries and the group's consolidating entries, and proposes posting rules. You stay in control at every step: previews of what would post, balanced-entry checks, and nothing posts until a person approves it.
Can I forecast, or is this only historical accounting?
You can plan forward. Once you've closed a month, the Plan surface puts your monthly statements and a scenario's assumptions in one grid spanning the actuals/forecast seam, so the forecast is driven by the same ledger the close produced, not a spreadsheet copied out of it. Scenarios are authored from your AI assistant over MCP today; the in-app editor is on the way.
Are there things my AI assistant can do that the app cannot?
Yes, deliberately. Every write operation on the platform becomes an MCP tool the day it ships, while screens follow where they earn their place. Authoring a forecast scenario and defining a new metric run from Claude, ChatGPT, or any MCP client today without a dedicated form in the app. A new posting rule is written by your AI too, and waits in Posting Rules until a person approves it. Anything you drive that way lands in the same ledger and shows up on the same screens.
I look after several clients. Can I see them all here?
Yes. Each client gets its own isolated graph (a client with several companies keeps them together in one), and you switch between them from one account. In your AI chat, add the RoboLedger connector once per graph and ask across all of them. It's built for fractional CFOs, controllers, and firms who look after more than one company. Harbinger FinLab walks you through your first client on a screenshare and trains your staff, so the second client is a playbook, not a project.
How do I get started, and what does it cost?
$99 a month per graph on the RoboSystems Standard plan, and a group's companies share one graph. Comparing against public companies adds the SEC subscription. Create an account, provision a graph with RoboLedger enabled, connect your books and ask your AI the first question. It's open source with no outside investors, so nobody can reprice it or shut it down on you. See plans
What if we don't have anyone to run it?
RoboLedger is run by your own accountant, bookkeeper or fractional CFO, working from the AI chat they already use. If you don't have one yet, Harbinger FinLab will point you to a practice that runs RoboLedger. Harbinger implements and trains; it never keeps anyone's books.
See it on your own books
Connect QuickBooks and ask your AI the first question. Nothing writes to QuickBooks until you post an entry.
$99 a month for the whole group's books. Open source, so it's yours. See plans
Already have an account? LoginView on GitHub