# RoboSystems

> One knowledge graph for your company's data, the companies around it, and public SEC filings, with document search and MCP tools for your AI.

RoboSystems is an open-source (Apache 2.0) platform for financial knowledge graphs, built and operated by RFS LLC. It holds a shared SEC XBRL repository of public-company filings and per-company graphs synced from QuickBooks, and serves both over MCP at https://api.robosystems.ai/v1/mcp, so Claude, ChatGPT, or any MCP client can query them. RoboLedger (https://roboledger.ai) is the ledger product built on it.

## Product
- [Platform](https://robosystems.ai/platform): what the platform does
- [Pricing](https://robosystems.ai/pricing)
- [Enterprise](https://robosystems.ai/enterprise): dedicated deployments
- [About](https://robosystems.ai/about): who builds it and the company behind it

## Guides
- [RoboSystems guides](https://robosystems.ai/docs/guides): Use RoboSystems through Claude, ChatGPT and other MCP clients. Connect a client, choose a graph, analyze SEC filings, and understand credits.
- [Connect Claude, ChatGPT or any MCP client](https://robosystems.ai/docs/guides/connect-an-mcp-client): Add RoboSystems to Claude, ChatGPT, Claude Code, Cursor or VS Code with one address. Sign in, choose a graph, and start asking.
- [Sign-in and graph access](https://robosystems.ai/docs/guides/oauth-and-graph-scope): What the RoboSystems consent screen asks, why one connection reaches one graph, how to switch graphs, and how to revoke an app's access.
- [Skills and the RoboSystems plugin](https://robosystems.ai/docs/guides/skills-and-the-plugin): Skills teach your AI assistant a multi-step job on RoboSystems and the mistakes to avoid. The four skills, how to install them, and what to do without them.
- [Analyze SEC filings with Claude or ChatGPT](https://robosystems.ai/docs/guides/sec-filings): Connect an AI client to the SEC filings graph: financial statements, cross-company comparisons, disclosures and filing text for 8,000+ companies.
- [Graphs, tiers and credits](https://robosystems.ai/docs/guides/graphs-tiers-and-credits): What a RoboSystems graph is, how tiers differ, what uses credits and what doesn't, and what happens when a graph runs out.
- [Find your way around the app](https://robosystems.ai/docs/guides/the-robosystems-app): A tour of robosystems.ai: graphs, MCP, console, documents, memory, the data lake, subgraphs, backups and billing.
- [Ask questions in the Console](https://robosystems.ai/docs/guides/console): The Console is RoboSystems' own AI on a graph. Questions use credits from your plan. Claude and ChatGPT do not.
- [Documents and memory](https://robosystems.ai/docs/guides/documents-and-memory): Keep policies and notes on a graph, search them, and store memories your AI assistant can recall later.
- [Data lake, subgraphs and backups](https://robosystems.ai/docs/guides/data-lake-and-subgraphs): Stage and query tables, create subgraphs for experiments, and download backups. All of it lives on the graph's instance.
- [Security and your data](https://robosystems.ai/docs/guides/security-and-your-data): How RoboSystems keeps each graph separate, encrypts it, controls sign-in, and what an AI client or RoboSystems' own AI sees of your data.
- [Take your data with you](https://robosystems.ai/docs/guides/take-your-data-with-you): Every way to get your data out of RoboSystems, from report files to the graph's database, and what happens when you disconnect, cancel or leave.
- [Invite your team](https://robosystems.ai/docs/guides/teams-and-roles): Invite people to your organization, give them a role on each graph, and remove them. What owners, admins, members and viewers can each do.

## Technical docs
- [Technical documentation](https://robosystems.ai/docs/technical): RoboSystems is an open-source, AI-native financial intelligence platform for accounting, financial reporting, and investment management.
- [Quick Start](https://robosystems.ai/docs/technical/quick-start): Create a RoboSystems account and API key, get a graph, and run your first authenticated query against the hosted API at https://api.robosystems.ai.
- [Core Concepts](https://robosystems.ai/docs/technical/core-concepts): A glossary of the terms that run through RoboSystems: graph_id, tiers, subgraphs, Elements, block envelopes, operators, and the two graph stores.
- [Architecture Overview](https://robosystems.ai/docs/technical/architecture-overview): How RoboSystems is built: the knowledge graph at the center, the operational and analytical planes around it, and the AWS infrastructure a fork deploys.
- [Authentication & API Keys](https://robosystems.ai/docs/technical/authentication-and-api-keys): API keys, browser sessions, and MCP OAuth: how each authenticates to the RoboSystems API, and how roles and graph membership decide what it reaches.
- [Operations Contract](https://robosystems.ai/docs/technical/operations-contract): Graph and extension writes in RoboSystems are named operations sharing one contract: one URL shape, response envelope, retry key, and progress stream.
- [Errors and Rate Limits](https://robosystems.ai/docs/technical/errors-and-rate-limits): Every RoboSystems endpoint reports failure the same way: a non-2xx status and a small JSON body with a detail and a request_id.
- [Versioning and Compatibility](https://robosystems.ai/docs/technical/versioning-and-compatibility): What stays stable as RoboSystems evolves, and where to read about what changed.
- [Graphs & Multi-Tenancy](https://robosystems.ai/docs/technical/graphs-and-multi-tenancy): RoboSystems is multi-tenant at the graph layer: every customer dataset lives in its own isolated graph database keyed by a graph_id.
- [Graph Operations](https://robosystems.ai/docs/technical/graph-operations): Graph operations change a graph's lifecycle — subgraphs, backups, tier, materialization, metadata and deletion — through one command endpoint.
- [Querying the Analytical Graph](https://robosystems.ai/docs/technical/querying-the-analytical-graph): Query the analytical graph — the LadybugDB projection of a graph's data — with Cypher, with SQL over its DuckDB staging tables, or through MCP tools.
- [File Uploads](https://robosystems.ai/docs/technical/file-uploads): File uploads load bulk node and relationship data into a custom (generic) graph: parquet, CSV or JSON files go straight to S3, are staged, then ingested.
- [Credits & Billing](https://robosystems.ai/docs/technical/credits-and-billing): In RoboSystems, only AI operations consume credits — every database, graph, MCP, Cypher, import, sync, backup, and schema operation is free.
- [Building Custom Integrations](https://robosystems.ai/docs/technical/building-custom-integrations): An integration is the supported way to connect your own data sources to RoboSystems: a small program in its own repository that calls the public API.
- [Build a Ledger Integration](https://robosystems.ai/docs/technical/build-a-ledger-integration): A ledger integration posts business events from an external system into a RoboLedger graph, and this tutorial builds one end to end.
- [AI Operators & MCP](https://robosystems.ai/docs/technical/ai-operators-and-mcp): Every RoboSystems graph is an MCP server; this page covers connecting a client, the full tool catalog, and the Operator endpoint that runs a model.
- [Search & AI Retrieval](https://robosystems.ai/docs/technical/search-and-ai-retrieval): Search gives an AI Operator hybrid keyword and semantic search over your own documents and SEC filing narratives, plus a memory store of its own.
- [Document Management](https://robosystems.ai/docs/technical/document-management): Every graph you own carries a document store for policies, procedures and notes, written as markdown and indexed for search.
- [Shared Repositories](https://robosystems.ai/docs/technical/shared-repositories): A shared repository is a platform-managed, read-only public dataset you subscribe to and query alongside your own graphs.
- [SEC Data Model & Query Rules](https://robosystems.ai/docs/technical/sec-data-model-and-query-rules): This page is for integrators querying the hosted sec graph — the shared repository of public-company XBRL filings — with Cypher.
- [Extensions Surface Overview](https://robosystems.ai/docs/technical/extensions-surface-overview): The extensions surface is the read/write API layer for RoboSystems product extensions (RoboLedger and RoboInvestor).
- [GraphQL Reads](https://robosystems.ai/docs/technical/graphql-reads): GraphQL gives you ad-hoc, strongly-typed reads over a graph's operational (OLTP) extensions data: ledger, investor and taxonomy records as they stand now.
- [RoboLedger Operations](https://robosystems.ai/docs/technical/roboledger-operations): RoboLedger's command writes and analytical views are graph-scoped operations at POST /extensions/roboledger/{graph_id}/operations/{op_name}.
- [QuickBooks Sync & Write Policy](https://robosystems.ai/docs/technical/quickbooks-sync-and-write-policy): This page covers how a connected QuickBooks Online company moves data into a RoboLedger graph, and how entries RoboLedger drafts move back out.
- [Chart of Accounts Mapping](https://robosystems.ai/docs/technical/chart-of-accounts-mapping): Mapping ties each account in a tenant's chart of accounts to an rs-gaap reporting concept. It is the join every statement depends on.
- [Period Close](https://robosystems.ai/docs/technical/period-close): Closing a month in RoboLedger is one atomic operation that checks the month is ready, posts its entries, stamps its statements and records a receipt.
- [Forecasting & Metrics](https://robosystems.ai/docs/technical/forecasting-and-metrics): RoboLedger plans and measures in the same shape it reports in. A forecast is a scenario authored as an Information Block.
- [RoboInvestor Operations](https://robosystems.ai/docs/technical/roboinvestor-operations): RoboInvestor's API is six command operations for securities and portfolio blocks, plus GraphQL reads of portfolios, positions and holdings.
- [Information Blocks](https://robosystems.ai/docs/technical/information-blocks): An Information Block is the platform's unit of financial meaning: the numbers, plus the concepts, structure, and rules that make them facts.
- [Information Block Reference](https://robosystems.ai/docs/technical/information-block-reference): The field-level reference for Information Blocks: the envelope, each block type's mechanics and operations, the rule patterns, and the view projections.
- [Event-Driven Ledger](https://robosystems.ai/docs/technical/event-driven-ledger): RoboLedger treats business events as the durable truth and the general ledger as something derived from them.
- [Event Block Reference](https://robosystems.ai/docs/technical/event-block-reference): The reference for the Event Block: its fields, vocabularies, transitions and handlers, the ledger records a handler writes, and the graph edges they become.
- [Taxonomy & Frameworks](https://robosystems.ai/docs/technical/taxonomy-and-frameworks): RoboSystems treats accounting vocabulary as data: concepts, hierarchies, calculation arcs, and rules are versioned rows seeded from JSON-LD packages.
- [Reporting & Rendering](https://robosystems.ai/docs/technical/reporting-and-rendering): RoboSystems renders financial statements once, on the server, from atomic facts — and ships the result to any consumer as light JSON.
- [Serialization & Export](https://robosystems.ai/docs/technical/serialization-and-export): A published RoboLedger report downloads as a file in three formats: the holon (JSON-LD), the Tavi compiled model, and an XBRL 2.1 package.
- [Local Development](https://robosystems.ai/docs/technical/local-development): Run the open-source RoboSystems platform on your own machine to develop against it, contribute to it, or evaluate it before deploying your own.
- [Windows Setup (WSL2)](https://robosystems.ai/docs/technical/windows-setup-with-wsl2): Run the RoboSystems stack on Windows through WSL2, with the repository stored inside the Linux filesystem rather than on a Windows drive.
- [Self-Hosted AI Models](https://robosystems.ai/docs/technical/self-hosted-ai-models): The server-side AI operators can run on an open-weight model through any OpenAI-compatible server, so the platform's AI does not depend on one vendor.
- [Connecting QuickBooks Locally](https://robosystems.ai/docs/technical/connecting-quickbooks-locally): This tutorial connects a QuickBooks Online company to a self-hosted RoboSystems stack, from registering an Intuit app to watching the first sync run.
- [Bootstrap Guide](https://robosystems.ai/docs/technical/bootstrap-guide): Bootstrap a fork of RoboSystems into your own AWS account: GitHub OIDC roles, secrets and feature flags, the first deploy, releases, and the frontend apps.
- [Enterprise SSO & SCIM](https://robosystems.ai/docs/technical/enterprise-sso-and-scim): This guide covers the enterprise identity plane: OIDC single sign-on for login and SCIM 2.0 for user provisioning and deprovisioning.
- [Security & Compliance](https://robosystems.ai/docs/technical/security-and-compliance): This guide covers RoboSystems' security posture and the optional, off-by-default compliance infrastructure you can enable when you deploy a fork.
- [Pipeline Guide](https://robosystems.ai/docs/technical/pipeline-guide): RoboSystems uses Dagster to orchestrate every pipeline that feeds the knowledge graph: SEC XBRL filings, connector syncs, and ledger writes.
- [RoboLedger Demos](https://robosystems.ai/docs/technical/roboledger-demo-walkthrough): The RoboLedger demos load synthetic books into a graph and exercise ingest, mapping, period close, reporting, and XBRL export, with no QuickBooks connection.
- [Getting Started with the SEC XBRL Pipeline](https://robosystems.ai/docs/technical/sec-xbrl-pipeline): The SEC XBRL pipeline turns EDGAR filings into the sec graph: the hosted repository you subscribe to, or a copy you load and query on your own stack.
- [Custom Graph Schema - Complete Guide](https://robosystems.ai/docs/technical/custom-graph-schema): A custom graph carries your own node and relationship types, declared in a schema.json; this page covers the schema format and a runnable demo.
- [REST API reference](https://robosystems.ai/docs/api): a page per operation
- [Extensions reference](https://robosystems.ai/docs/extensions): the RoboLedger and RoboInvestor operations and GraphQL reads

## Blog
- [What Is Financial Intelligence? The Layer AI Needs Before It Touches a Number](https://robosystems.ai/blog/what-is-financial-intelligence): What is financial intelligence? The layer AI needs before it can work on the books: a knowledge graph, a knowledge base and memory, with a person in the loop.
- [Semantic Sovereignty: The Missing Layer of Sovereign AI](https://robosystems.ai/blog/semantic-sovereignty): Semantic sovereignty defined: owning the meaning layer of your AI stack. Why infrastructure sovereignty is not enough, and why finance is where it matters most.
- [The Coverage Machine: Turning SEC Filings Into Narrated Equity Research, in the Open](https://robosystems.ai/blog/the-coverage-machine): How we turn SEC filings into narrated equity research: AI analysis on structured XBRL, a human-crafted deck, and automated production — open source.
- [Events, Not Transactions: A Better Foundation for the Ledger](https://robosystems.ai/blog/events-not-transactions): Why RoboLedger records the economic event first and derives double-entry transactions from it—an REA-grounded ledger that stays explainable and AI-operable.
- [Financial Reports as DataBooks: One Artifact for Humans, Machines, and LLMs](https://robosystems.ai/blog/financial-reports-as-databooks): A proof of concept rendering published financial reports as DataBooks—human-readable Markdown plus addressable RDF/Turtle, with SHACL and XBRL validation evidence inlined. Queryable, verifiable, self-describing.
- [Information Blocks: Turning Transaction Line Items Into Financial Reports](https://robosystems.ai/blog/information-blocks): How Information Blocks turn transaction line items into financial statements and let you author schedules—one self-describing primitive behind every accounting artifact.
- [The Open SEC Data Repository: Every Filing as a Queryable Graph](https://robosystems.ai/blog/open-sec-data-repository): The RoboSystems SEC repository turns every XBRL filing into a queryable financial graph—provenance to the source, open source, and self-hostable. Run your own analysis on any public company.
- [What a Financial Standard Actually Standardizes: Structure vs. Content](https://robosystems.ai/blog/structure-vs-content): A financial reporting standard standardizes structure, not content. Here is what that distinction means for XBRL, US GAAP, and how RoboLedger keeps your books yours.
- [From Numbers to Narratives: Bridging Structured Data and Document Search](https://robosystems.ai/blog/from-numbers-to-narratives): How RoboSystems bridges structured financial data in a knowledge graph with full-text document search across SEC filings, enabling AI to reason over both numbers and narratives.
- [Building Financial Context Graphs: Beyond RAG to Semantic Understanding](https://robosystems.ai/blog/building-financial-context-graphs): Context graphs are the semantic layer that transforms scattered financial data into meaning AI can actually understand. Learn how to build them on the RoboSystems knowledge graph platform.
- [The Future Data Stack: Why We Built RoboSystems](https://robosystems.ai/blog/the-future-data-stack): Learn how RoboSystems is architected for the future of data engineering. From Dagster-powered orchestration to self-hosted deployments, discover why the next decade belongs to unified, AI-native platforms.
- [Knowledge Graphs: The Missing Link in Financial Intelligence](https://robosystems.ai/blog/understanding-knowledge-graphs-finance): Understand how knowledge graphs revolutionize financial analysis. Learn why relationships matter more than transactions and how to build your financial knowledge graph.
- [AI Agents for Financial Analysis: Beyond ChatGPT](https://robosystems.ai/blog/ai-agents-financial-analysis): Learn how MCP-enabled AI agents transform financial analysis. Discover AI that executes analysis, monitors patterns, and generates insights—not just advice. Real examples included.
- [The Financial Knowledge Graph Manifesto](https://robosystems.ai/blog/financial-knowledge-graph-manifesto): Discover why financial knowledge graphs are inevitable. Learn how graph databases transform disconnected financial data into navigable intelligence that reveals hidden patterns and opportunities.