The Knowledge Graphfor Financial Data
Your company, the companies around it, and the public record, in one knowledge graph. Your AI queries the facts, reads the documents behind them, and remembers the work from one session to the next, in Claude, ChatGPT, or any MCP client.
How It Works
Every Number, in Context
A figure on its own answers nothing. RoboSystems keeps each fact with the company, report, concept and period it belongs to, the passage that explains it, and what your team decided about it last time—the three layers your AI reads before it answers.
What This Enables
Multi-Hop Reasoning
AI traverses relationships across structured data and documents to answer complex questions spanning multiple sources.
“What drove the change in gross margin compared to industry peers last quarter?”
Numbers + Narratives
AI doesn't just know the numbers—it reads the context. Search risk factors by keyword, find the XBRL tags in those disclosures, then query actual figures across periods.
“Why did goodwill drop?” → searches disclosure, finds impairment, queries the fact
Institutional Memory
The bridge between the two: the graph holds what happened, documents what was disclosed, memory how your team handled it.
“How did we classify this vendor last quarter, and why?”
How We Deliver It
A modern stack purpose-built for financial intelligence—knowledge graph, document search, and AI memory in one platform.
LadybugDB Engine
Purpose-built graph database optimized for analytical workloads and AI-native applications.
- •Columnar storage for fast aggregations
- •DuckDB staging for data validation
- •LanceDB vector indexes for semantic search
- •Subgraph workspaces for AI memory and isolation
Document Search
Hybrid search across your documents and public filings, powered by OpenSearch.
- •Full-text and semantic search with hybrid scoring
- •Search across structured and unstructured data
- •Search MD&A, risk factors, and iXBRL disclosures
Open Source
Fork, deploy, and extend. Complete infrastructure automation with Docker, CloudFormation, and GitHub Actions.
- •TypeScript, Python, and MCP clients
- •Docker development environment
- •One-command AWS deployment
- •GitHub OIDC — no stored credentials
MCP Protocol
Native integration with AI agents through the Model Context Protocol standard.
- •Works with Claude, ChatGPT, Grok, and any MCP client
- •Schema introspection and typed GraphQL reads
- •Cypher queries from natural language
- •OAuth sign-in or API key authentication
API & SDKs
Platform REST API — Extensions GraphQL for reads, CQRS operations for writes.
- •Extensions GraphQL with per-graph schema introspection
- •Named operations with idempotency and audit trail
- •TypeScript and Python SDKs with full types
- •SSE streaming for real-time operation progress
Security & Isolation
A dedicated graph-database instance per subscription, or your own AWS account on a Dedicated Deployment.
- •Tested cross-tenant isolation
- •Encryption at rest and in transit
- •Passkeys, plus SSO and SCIM on Dedicated Deployments
- •SOC 2 Type II compliance in progress · Deployment options · Trust Center
Applications Powered by RoboSystems
Purpose-built applications that leverage the RoboSystems platform to deliver intelligent financial reporting, document search, and investment research capabilities.
How It Works
API
Graph
RoboLedger syncs QuickBooks into the RoboLedger schema for full ledger management, period close, AI-native financial reporting, and forward planning. RoboInvestor manages investment portfolios and provides access to the SEC Shared Repository for securities research. Both expose MCP tools, so any AI assistant can run natural language queries against the knowledge graph.
Inside your company
RoboLedger
AI-Native Financial Reporting
A complete accounting close platform — connect your data sources, let AI triage every transaction, close the books, generate XBRL-compliant financial reports, and plan the months ahead off the same ledger.
Connections
- •QuickBooks over OAuth2 with on-demand sync
- •Chart of accounts, journal entries, and transactions
- •Trial balance with full debit/credit detail
Ledger, Close & Reporting
- •Event-driven inbox — AI pre-classifies, you approve
- •AI auto-maps chart of accounts to US-GAAP with confidence scores
- •Live Balance Sheet, Income Statement, and Cash Flow — no close required
- •Guided period close — fiscal calendar, depreciation and prepaid schedules, rule-engine gating
- •Report Creator — Tavi and XBRL 2.1 export with publish lists
Planning & Analysis
- •Plan — actuals and forecast in one monthly grid
- •Block Explorer — any number down to the facts and rules behind it
Agents & MCP
- •AI Console — ask about your books in plain English
- •Your AI assistant drives the close over MCP — author scenarios, define metrics, write handler rules
- •Push approved entries back to the source system
Outside your company
RoboInvestor
Investment Portfolio & AI Research
Track public and private positions in one book, research any public company against the SEC knowledge graph, and read equity research generated from the filings.
Portfolio Management
- •PE & VC positions with full terms: SAFEs, notes, LLC units, LP interests, warrants, options, and RSUs
- •Cost basis, valuations, and holdings rolled up per issuer
- •Cross-graph linking — a holding connects to its issuer's own graph
SEC Research Console
- •75,000+ XBRL filings across 8,000+ public companies
- •AI-powered deep research — plain-English questions become graph queries
- •Statements rendered from the XBRL, not PDF scans
- •Full-text and semantic search across filings and your own documents
- •MCP tools for Claude, ChatGPT, Grok, and any MCP client
Equity Research
- •One company per report, every figure traceable to its filing
- •Narrated video brief alongside the written report
- •Quarterly continuing coverage with full report history
SEC XBRL Repository
Every Public Company. Numbers and Narratives.
Structured XBRL facts in a knowledge graph, plus full-text and semantic search across MD&A, risk factors, and disclosure notes. Subscribe once and your AI agents gain instant access to market intelligence—no data pipeline setup required.
MCP Clients
Use with Claude, ChatGPT, Grok, or any MCP-compatible AI client, no install required.
Published in the ChatGPT plugin directoryMCP Protocol
Paste one URL and sign in.
https://api.robosystems.ai/v1/graphs/sec/mcpAPI & SDKs
npm i @robosystems/clientpip install robosystems-clientBuild on RoboSystems
Connect your data sources, write your own integrations, and build applications and agents on the same public API that RoboLedger and RoboInvestor run on.
Official Integrations
QuickBooks
Accounting
Sync your chart of accounts, transactions, and trial balance. Full OAuth integration with on-demand sync.
Need a QuickBooks account? →SEC XBRL
Public Filings
XBRL facts from 8,000+ public companies in a shared graph, full-text and semantic search across the filings, and the Analyst Operator for plain-English questions. Updated daily, nothing to import.
See the SEC Repository →Mercury
Business Banking
Connect your Mercury accounts with OAuth. Posted transactions land in your ledger's inbox with a suggested category, ready to review and post.
Plaid
Bank Feeds
Link bank and card accounts at other institutions. Transactions flow into the same inbox—nothing posts to the ledger until you approve it.
Build Your Own Integrations
Connect any source without touching the platform. An integration is a small program in its own repository that writes to RoboSystems through the public API with an API key. It never runs inside the platform—so it survives every release, runs identically against the managed cloud or a self-hosted deployment, and your source credentials stay on your side.
Ledger
Business events from any system you run — invoices, payments, payroll — landed in an inbox for approval.
What we enforce
- •Double-entry balance
- •Capture, then approve
- •Closed-period gate
- •Idempotent per source event
Semantic facts
A custom vocabulary, then observed values per period — usage counts, operational KPIs.
What we enforce
- •Typed concepts
- •Presentation structure
- •Replace per period
- •Provenance on every fact
Raw graph
Parquet or CSV files, staged and materialized into graph nodes and relationships.
What we enforce
- •Per-graph schema
- •Bulk ingestion pipeline
- •Staging you can query
Nothing to stand up: the template ships a GitHub Actions schedule and a Claude Code setup—fill in collect and transform, set two repo secrets, and it runs.
Start from the integration template, see a working example, or read the integration guide.
Clients & SDKs
The same surface the applications above are built on. Every graph is a remote MCP server, and typed clients cover the REST API end to end.
MCP Endpoint
Every graph is a remote MCP server — one URL, sign in, no install
https://api.robosystems.ai/v1/mcpTypeScript Client
Full-featured client for JavaScript and TypeScript applications
npm install @robosystems/clientBuilding an application on RoboSystems?
Open Source Foundation
RoboSystems is committed to open source. Fork and self-host the entire platform, contribute to development, or use our managed service for hassle-free AI-powered financial analysis tools.
RoboSystems GitHub
The heart of the RoboSystems ecosystem - our main repository contains the complete knowledge graph platform including the API server, semantic data processing, infrastructure templates, and deployment workflows. Everything you need to run your own financial knowledge graph - locally or in your cloud infrastructure.
Why Open Source?
- Semantic Sovereignty
Own what your numbers mean. Definitions, taxonomies, and calculation logic are open, inspectable artifacts—because a black box in your own cloud is still a black box. Read the essay
- Community Innovation
Accelerate development with contributions from developers worldwide.
- Security Through Scrutiny
Open code means more eyes finding and fixing potential issues.
- Foundation Technology
Following XBRL and Arelle's footsteps in creating open financial standards for the AI age.
Enterprise Services
The platform is open source. We help you succeed with it.
- •Custom Integrations—connect your ERP, banking, or proprietary data sources
- •Implementation Support—deployment, training, and onboarding for your team
- •AI Support Agents—ongoing maintenance and optimization of your knowledge graph
- •Dedicated Deployment—your own AWS account, operated by us, with SSO and SCIM
Fork & Deploy
Deploy your own instance with secure GitHub OIDC—no AWS credentials stored in GitHub. Full CloudFormation templates and GitHub Actions workflows included.
Bootstrap GuideDownload RoboSystems
MCP Client and Developer Tools
Official packages for integrating with RoboSystems.
Local Development
# Clone and install tools
git clone https://github.com/RoboFinSystems/robosystems
cd robosystems
brew install uv just
# Start local Docker stack
just start
# API at http://localhost:8000For production deployment, see the Bootstrap Guide.
Join the RoboSystems Community
Be part of building the future of financial AI infrastructure
Development & Contribution
- •Track our roadmap and upcoming features
- •Submit pull requests and contribute code
- •Review source code and architecture
- •Fork and customize for your needs
🤝 Community Support
- •Report bugs and request features
- •Join discussions on architecture decisions
- •Share your implementations and use cases
- •Get help from maintainers and community
Ready to Connect Your Financial Data?
Structured data, searchable documents, and AI memory in one platform—powering intelligent automation and insights.
Already have an account? Login