# RocketRide Documentation > RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production. MIT licensed. Run the engine free on your own machine with Docker, the VS Code extension or a native download, or use RocketRide Cloud. Use it from MCP, the CLI, the Python or TypeScript SDK, or the VS Code extension. Use RocketRide when: - You want to build, test and run agents and AI pipelines (LLM calls, RAG, document processing, OCR, PII anonymization) and take them to production. - You want one runtime you can self-host or run on RocketRide Cloud, used from MCP, the CLI, the Python and TypeScript SDKs, or your IDE. - You want to run CrewAI, LangChain, LlamaIndex or Deep Agent agents as nodes in one pipeline. ## Start here - [Use RocketRide from a coding agent](https://docs.rocketride.ai/quickstart/coding-agents.md): Start page for coding agents. Run the engine locally in Docker, check it is up, use it from the CLI, SDK or MCP, and find the machine-readable docs. ## Home - [RocketRide Documentation](https://docs.rocketride.ai/index.md): RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Pipelines are portable JSON that run the same way on your laptop, your servers, or RocketRide Cloud. ## Get Started - [Quickstart](https://docs.rocketride.ai/quickstart.md): Pick how you want to build: the VS Code IDE, an SDK, the CLI, or a coding agent over MCP. Each path takes you from zero to a running pipeline. - [Run from the CLI](https://docs.rocketride.ai/quickstart/cli.md): The rocketride command-line tool runs pipelines from a terminal, the same operations the SDKs expose, no code required. Install with pip or npm. - [Build a pipeline in your IDE](https://docs.rocketride.ai/quickstart/ide-walkthrough.md): The visual canvas in the VS Code extension is the fastest way to author a .pipe file. Start from zero and finish with a running Chat to LLM pipeline. - [Integrate a pipeline with an SDK](https://docs.rocketride.ai/quickstart/sdk-integration.md): Once you have a .pipe file, run it from your own application with the Python or TypeScript SDK against a local engine or RocketRide Cloud. ## Concepts - [Understanding RocketRide](https://docs.rocketride.ai/concepts.md): RocketRide has a few moving parts. Once you know how they fit together, the rest of the docs map cleanly onto them. - [Agents & Tools](https://docs.rocketride.ai/concepts/agents-tools-skills.md): An agent reasons in a loop, deciding which model to call, which tools to use, and when it is done. It needs an LLM, optionally tools, and sometimes memory. - [Apps](https://docs.rocketride.ai/concepts/apps.md): A RocketRide app is a user interface that runs inside the RocketRide shell against your engine. The shell provides sign-in, the connection, and settings. - [Execution Model](https://docs.rocketride.ai/concepts/execution-model.md): A pipeline describes what to run; the execution model is how the engine runs it. Data lanes carry data between nodes; control links join agents to helpers. - [Nodes](https://docs.rocketride.ai/concepts/nodes.md): A pipeline is a graph and nodes are its vertices. Each node does one job, such as calling a model, embedding text, or querying a vector store. - [Pipelines](https://docs.rocketride.ai/concepts/pipelines.md): A pipeline is the unit of work in RocketRide: a directed graph of components that move and transform data, authored as .pipe files (JSON) and run by the engine. - [Runtime & Engine](https://docs.rocketride.ai/concepts/runtime-engine.md): The engine is the RocketRide runtime that loads a .pipe definition, brings its nodes to life, and moves data through the graph until the work is done. ## Clients - [RocketRide Client Libraries](https://docs.rocketride.ai/clients.md): Official client libraries for the RocketRide Engine. The TypeScript and Python clients talk to the engine the same way and share one core API. - [Python SDK](https://docs.rocketride.ai/clients/python.md): Build, run, and manage AI pipelines from Python. - [Analytics](https://docs.rocketride.ai/clients/python/analytics.md): rocketride.analytics mints bound per-app event reporters, bare bones by design. - [Chat](https://docs.rocketride.ai/clients/python/chat.md): Conversational pipelines: build a Question, send it with client.chat(), and parse the response with Answer. Class tables in the API reference. - [Configuration](https://docs.rocketride.ai/clients/python/configuration.md): Everything the RocketRideClient constructor accepts, the environment variables it reads, and how its timeouts, reconnection, and debug hooks behave. - [Connection](https://docs.rocketride.ai/clients/python/connection.md): How the client attaches, authenticates, stays connected, and shuts down. The full method tables live in the API reference. - [Sending Data](https://docs.rocketride.ai/clients/python/data.md): Get data into a running pipeline: one-shot sends, file uploads with progress, and chunked streaming. Method tables in the API reference. - [Deployments](https://docs.rocketride.ai/clients/python/deploy.md): Persist pipelines server-side and run them on a schedule. Accessed via client.deploy; full method tables in the API reference. - [Error Handling](https://docs.rocketride.ai/clients/python/errors.md): What the SDK raises, when, and how to catch it. - [Examples](https://docs.rocketride.ai/clients/python/examples.md): Complete, runnable programs covering the SDK surface end to end. - [Run Logs (client.log)](https://docs.rocketride.ai/clients/python/logs.md): Every task writes a run log: one continuous JSONL event stream per task identity (project_id + source, plus the scope: a team_id addresses that team's DEPLOY… - [OpenTelemetry Bridge (rocketride otel)](https://docs.rocketride.ai/clients/python/otel-bridge.md): The OpenTelemetry bridge exports live pipeline traces and metrics from a running RocketRide engine to any OpenTelemetry collector over OTLP. - [Pipeline Diff (rocketride diff)](https://docs.rocketride.ai/clients/python/pipe-diff.md): A raw git diff of a .pipe file is dominated by canvas coordinate churn: nudge a node and its ui.position x/y move, pan or zoom and the top-level viewport… - [Running Pipelines](https://docs.rocketride.ai/clients/python/pipelines.md): Start a pipeline, watch its progress, and stop it. Method tables live in the API reference; this page covers the workflow. - [API Reference](https://docs.rocketride.ai/clients/python/reference.md): The core public surface of the Python SDK. Constructor options and environment variables are on Configuration; exceptions on Error Handling. - [File Storage](https://docs.rocketride.ai/clients/python/storage.md): Read, write, and manage files in your account's server-side store. - [TypeScript SDK](https://docs.rocketride.ai/clients/typescript.md): Build, run, and manage AI pipelines from Node.js or the browser. - [Analytics](https://docs.rocketride.ai/clients/typescript/analytics.md): rocketride/analytics mints bound per-app event reporters, bare bones by design. - [Chat](https://docs.rocketride.ai/clients/typescript/chat.md): Conversational pipelines: build a Question, send it with client.chat(), and parse the response with Answer. Class tables in the API reference. - [Configuration](https://docs.rocketride.ai/clients/typescript/configuration.md): Everything RocketRideClientConfig accepts, the environment variables the client reads, and how its timeouts, reconnection, and debug hooks behave. - [Connection](https://docs.rocketride.ai/clients/typescript/connection.md): How the client attaches, authenticates, stays connected, and shuts down. The full method tables live in the API reference. - [Sending Data](https://docs.rocketride.ai/clients/typescript/data.md): Get data into a running pipeline: one-shot sends, concurrent file uploads with progress, and chunked streaming. Method tables in the API reference. - [Drizzle over Pipelines](https://docs.rocketride.ai/clients/typescript/database-drizzle.md): The rocketride/drizzle entry point builds a Drizzle ORM instance whose Postgres driver transports SQL over a RocketRide pipeline instead of a TCP socket. - [Sequelize over Pipelines](https://docs.rocketride.ai/clients/typescript/database-sequelize.md): client.database.sequelize(options) builds a Sequelize v6 ORM instance whose Postgres dialect transports SQL over a RocketRide pipeline instead of a TCP socket. - [Deployments](https://docs.rocketride.ai/clients/typescript/deploy.md): Persist pipelines server-side and run them on a schedule. Accessed via client.deploy; full method tables in the API reference. - [Error Handling](https://docs.rocketride.ai/clients/typescript/errors.md): What the SDK throws, when, and how to catch it. - [Examples](https://docs.rocketride.ai/clients/typescript/examples.md): Complete, runnable programs covering the SDK surface end to end. - [Run Logs (client.log)](https://docs.rocketride.ai/clients/typescript/logs.md): Every task writes a run log: one continuous JSONL event stream per task identity (projectId + source, plus the scope: a teamId addresses that team's DEPLOY… - [Running Pipelines](https://docs.rocketride.ai/clients/typescript/pipelines.md): Start a pipeline, watch its progress, and stop it. Method tables live in the API reference; this page covers the workflow. - [API Reference](https://docs.rocketride.ai/clients/typescript/reference.md): The core public surface of the TypeScript SDK. Constructor options and environment variables are on Configuration; exceptions on Error Handling. - [File Storage](https://docs.rocketride.ai/clients/typescript/storage.md): Read, write, and manage files in your account's server-side store. - [Introduction](https://docs.rocketride.ai/clients/vscode.md): RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. - [App Builder](https://docs.rocketride.ai/clients/vscode/app-builder.md): The App Builder is the extension's workbench for building apps that run inside the RocketRide shell. - [Cloud Sign-In](https://docs.rocketride.ai/clients/vscode/cloud-sign-in.md): Signing in to RocketRide Cloud from the extension runs an OIDC authorization code flow with PKCE against Zitadel. - [Deployment Webview Protocol](https://docs.rocketride.ai/clients/vscode/deployment-webview.md): The deploy surfaces (the file view's DEPLOY page and the team-deployment record drawer) are rendered by shared UI components inside the Project webview. - [Google Account Sign-In](https://docs.rocketride.ai/clients/vscode/google-oauth.md): Nodes that talk to Google services (for example the Gmail tool) offer a "Login with Google" button in the node config panel. - [Installation](https://docs.rocketride.ai/clients/vscode/installation.md): On first launch, the extension shows a Welcome page to guide you through setup. - [Microsoft Account Sign-In](https://docs.rocketride.ai/clients/vscode/microsoft-oauth.md): Nodes that talk to Microsoft 365 services (Excel, Word, OneDrive, Outlook Mail, Outlook Calendar) offer a "Login with Microsoft" button in the node config… - [Usage Guide](https://docs.rocketride.ai/clients/vscode/usage.md): If a pipeline is already running on the server. ## Guides - [Advanced Agents](https://docs.rocketride.ai/guides/advanced-agents.md): Builds on Agents and Tools to cover multi-agent patterns, memory strategies, and safety techniques for production agent pipelines in RocketRide. - [Shell API](https://docs.rocketride.ai/guides/apps.md): A complete guide for developers building micro-frontend applications for the RocketRide Cloud platform. - [App Builder](https://docs.rocketride.ai/guides/apps/app-builder.md): The App Builder is the workspace in the RocketRide VS Code extension that takes an app from an empty folder to a version your team can open. - [Best Practices](https://docs.rocketride.ai/guides/best-practices.md): Practical guidance for building reliable, maintainable RocketRide pipelines. - [Error Handling](https://docs.rocketride.ai/guides/error-handling.md): Patterns for keeping RocketRide pipelines useful when things fail, with links to Troubleshooting for what can fail and WebSocket Events for the format. - [Observability](https://docs.rocketride.ai/guides/observability.md): Every RocketRide run is recorded. The mental model behind run logs, the two ways to watch a pipeline (live and replayed), and which surface to use. - [Performance](https://docs.rocketride.ai/guides/performance.md): Practical levers for making RocketRide pipelines faster and cheaper, with pointers to the Execution Model for why the levers exist. ## Examples - [Document Extraction](https://docs.rocketride.ai/examples/document-extraction.md): Read files from the local file system, parse them into structured text, extract specific fields, and return structured JSON in a RocketRide pipeline. - [RAG Pipeline](https://docs.rocketride.ai/examples/rag-pipeline.md): Retrieval-augmented generation (RAG) in RocketRide: embed documents into a vector store, then answer questions by retrieving chunks and feeding them to an LLM. - [Webhook Pipeline](https://docs.rocketride.ai/examples/webhook-pipeline.md): The simplest useful RocketRide pipeline: an HTTP endpoint that accepts a question, sends it to an LLM, and returns the answer. The hello world of RocketRide. ## Nodes - [Overview](https://docs.rocketride.ai/nodes.md) - [Accessibility Describe](https://docs.rocketride.ai/nodes/accessibility_describe.md): An accessibility-focused image analysis node that generates scene descriptions optimized for blind and visually impaired users. - [CrewAI Agent](https://docs.rocketride.ai/nodes/agent_crewai.md): Standalone single-agent CrewAI node. - [CrewAI Agent](https://docs.rocketride.ai/nodes/agent_crewai/crewai_agent.md): Standalone single-agent CrewAI node. - [CrewAI Manager](https://docs.rocketride.ai/nodes/agent_crewai/crewai_manager.md): Multi-agent manager using CrewAI hierarchical process. - [CrewAI Subagent](https://docs.rocketride.ai/nodes/agent_crewai/crewai_subagent.md): Managed CrewAI sub-agent. - [Deep Agent](https://docs.rocketride.ai/nodes/agent_deepagent.md): Single-agent execution using Deep Agents. - [Deep Agent](https://docs.rocketride.ai/nodes/agent_deepagent/deepagent_agent.md): Single-agent execution using Deep Agents. - [DeepAgent Subagent](https://docs.rocketride.ai/nodes/agent_deepagent/deepagent_subagent.md): Managed Deep Agent subagent. - [LangChain](https://docs.rocketride.ai/nodes/agent_langchain.md): Single-agent execution using LangChain. - [LlamaIndex](https://docs.rocketride.ai/nodes/agent_llamaindex.md): Single-agent execution using LlamaIndex's ReAct loop. - [RocketRide Wave](https://docs.rocketride.ai/nodes/agent_rocketride.md): Wave-planning agent built natively on the RocketRide architecture. - [Anomaly Detector](https://docs.rocketride.ai/nodes/anomaly_detector.md): A pipeline monitoring component that detects anomalies in numeric output values using statistical methods. - [Anonymize](https://docs.rocketride.ai/nodes/anonymize.md): A filter component that identifies and masks sensitive information in text data. - [Answers to Documents](https://docs.rocketride.ai/nodes/answer_documents.md): An adapter component that turns model/agent answers into embeddable documents. - [Aparavi AQL](https://docs.rocketride.ai/nodes/aparavi_aql.md): Queries the Aparavi data governance platform using AQL (Aparavi Query Language). - [Player](https://docs.rocketride.ai/nodes/audio_player.md): The Audio Player component plays audio through the system’s default audio output device, including the audio track from video content. - [Transcribe](https://docs.rocketride.ai/nodes/audio_transcribe.md): The Audio transcribe component recieves audio or video and transcribes into text. - [Text To Speech](https://docs.rocketride.ai/nodes/audio_tts.md): Converts incoming text into speech using Kokoro-82M (local KPipeline or --modelserver KokoroLoader). - [Authoritative Overlay](https://docs.rocketride.ai/nodes/authoritative_overlay.md): Cross-checks extracted financial numbers against the US SEC EDGAR company-concept API for a configured CIK, scoped to a filing period (form / fy / fp / start / end / frame). - [Background Removal](https://docs.rocketride.ai/nodes/background_removal.md): Foreground / background separation using BiRefNet (MIT). - [Caption](https://docs.rocketride.ai/nodes/caption.md): Generates a natural-language caption for an image using Florence-2 Base (MIT). - [Text Chunker](https://docs.rocketride.ai/nodes/chunker.md): A text chunking component that splits documents into smaller, semantically coherent chunks for downstream processing such as embedding, retrieval, and LLM-based generation. - [Text To Speech (ElevenLabs)](https://docs.rocketride.ai/nodes/cloud_tts.md): Converts incoming text into speech using the ElevenLabs text-to-speech API. - [Context Optimizer](https://docs.rocketride.ai/nodes/context_optimizer.md): A transformation component that manages LLM context window budgets. - [Core](https://docs.rocketride.ai/nodes/core.md): A combined configuration that bundles a preprocessor, embedding model, vector store, and LLM into a single selectable unit. - [Currency Convert (Explicit)](https://docs.rocketride.ai/nodes/currency_convert_explicit.md): An opt-in currency converter for the audit-grade financial extraction suite. - [ClickHouse](https://docs.rocketride.ai/nodes/db_clickhouse.md): A ClickHouse component that answers natural-language questions by translating them into SQL and executing them against the database, returning rows as a table, text, or structured answers. - [Firestore](https://docs.rocketride.ai/nodes/db_firestore.md): A processing component that connects to Google Cloud Firestore (Native mode). - [Hotdata](https://docs.rocketride.ai/nodes/db_hotdata.md): Creates one ephemeral Hotdata database for each pipeline run, or attaches to an existing one so agents in separate runs can share it. - [MySQL](https://docs.rocketride.ai/nodes/db_mysql.md): A processing component that takes structured table data and inserts it into a MySQL database. - [PostgreSQL](https://docs.rocketride.ai/nodes/db_postgres.md): A processing component that takes structured table data and inserts it into a PostgreSQL database. - [Depth Estimation](https://docs.rocketride.ai/nodes/depth_estimate.md): Monocular depth estimation using Depth Anything V2 Small (Apache-2.0). - [Object Detection](https://docs.rocketride.ai/nodes/detect.md): Per-frame object detection. - [Segmentation](https://docs.rocketride.ai/nodes/detect_segment.md): Pixel-level segmentation with HuggingFace-native engines: Mask2Former-instance (MIT, default) for closed-set instance masks; Mask2Former-semantic (MIT) for per-pixel class maps. - [Dictionary](https://docs.rocketride.ai/nodes/dictionary.md): A processing component that analyzes documents to extract a dictionary of key terms and phrases. - [Discord Bot](https://docs.rocketride.ai/nodes/discord.md): A Discord Bot source node that receives messages from channels and DMs via the Discord Gateway. - [Image](https://docs.rocketride.ai/nodes/embedding_image.md): A processing component that generates vector embeddings from image content using advanced computer vision models. - [OpenAI (Embedding)](https://docs.rocketride.ai/nodes/embedding_openai.md): A component that transforms text into numerical vector representations using advanced embedding models. - [Transformer](https://docs.rocketride.ai/nodes/embedding_transformer.md): A component that transforms text into numerical vector representations using advanced embedding models. - [Video](https://docs.rocketride.ai/nodes/embedding_video.md): A processing component that generates vector embeddings from video content by extracting frames at configurable intervals and encoding them using vision models such as CLIP. - [Data Extractor](https://docs.rocketride.ai/nodes/extract_data.md): A component that processes unstructured or semi-structured text and extracts structured data in a tabular format. - [Fact Extractor](https://docs.rocketride.ai/nodes/extract_facts.md): The extraction brain. - [Face Detection](https://docs.rocketride.ai/nodes/face_detection.md): Per-frame face detection using MediaPipe BlazeFace (Apache-2.0). - [Frame Grabber](https://docs.rocketride.ai/nodes/frame_grabber.md): A component that extracts frames from video files and outputs them as image data. - [ArangoDB](https://docs.rocketride.ai/nodes/graph_arango.md): A processing component that connects to an ArangoDB multi-model database. - [FalkorDB](https://docs.rocketride.ai/nodes/graph_falkordb.md): A processing component that connects to a FalkorDB graph database. - [HydraDB](https://docs.rocketride.ai/nodes/graph_hydradb.md): A database/tool node for HydraDB, a managed graph + memory store. - [Neo4J](https://docs.rocketride.ai/nodes/graph_neo4j.md): A processing component that connects to a Neo4J graph database. - [Guardrails](https://docs.rocketride.ai/nodes/guardrails.md): A comprehensive input/output guardrails filter for AI safety. - [Fingerprinter](https://docs.rocketride.ai/nodes/hash.md): A processing component that generates a unique fingerprint (hash) of a document's content. - [Cleanup](https://docs.rocketride.ai/nodes/image_cleanup.md): A component that processes an image, cleans it up for OCR tasks by converting to gray scale, removing noise, deskewing, and enhancing contrast. - [Image Orientation Fixer](https://docs.rocketride.ai/nodes/image_orient.md): Turns scanned photographs the right way up. - [Landing.ai Extract](https://docs.rocketride.ai/nodes/landing_ai.md): Extracts structured fields from parsed Markdown using Landing.ai ADE and a JSON Schema you upload. - [Extract](https://docs.rocketride.ai/nodes/landing_ai/extract.md): Extracts structured fields from parsed Markdown using Landing.ai ADE and a JSON Schema you upload. - [Parse](https://docs.rocketride.ai/nodes/landing_ai/parse.md): Parses documents with Landing.ai Agentic Document Extraction (ADE), extracting clean Markdown text and structured tables from PDFs, images, and spreadsheets using the DPT-2 model. - [LlamaParse](https://docs.rocketride.ai/nodes/llamaparse.md): A document parsing component that uses LlamaParse to extract text and structured data from various document formats including PDFs, images, Word documents, Excel spreadsheets, and other formats. - [Anthropic](https://docs.rocketride.ai/nodes/llm_anthropic.md): A component that integrates with Anthropic's Claude models for natural language understanding and generation. - [Baidu Qianfan](https://docs.rocketride.ai/nodes/llm_baidu_qianfan.md): A component that connects to Baidu Qianfan ERNIE large language models through Qianfan's OpenAI-compatible chat-completions API. - [Amazon Bedrock](https://docs.rocketride.ai/nodes/llm_bedrock.md): A component that connects to Amazon Bedrock, providing access to a range of foundation models from leading AI providers through a unified AWS interface. - [Deepseek](https://docs.rocketride.ai/nodes/llm_deepseek.md): A component that connects to DeepSeek’s large language models for advanced natural language processing. - [Gemini](https://docs.rocketride.ai/nodes/llm_gemini.md): A component that connects to Gemini models for advanced natural language processing. - [GLM (Z.ai)](https://docs.rocketride.ai/nodes/llm_glm.md): A component that connects to Zhipu AI's GLM large language models for advanced natural language processing. - [GMI Cloud](https://docs.rocketride.ai/nodes/llm_gmi_cloud.md): A component that connects to GMI Cloud's large language models for advanced natural language processing. - [IBM Watson](https://docs.rocketride.ai/nodes/llm_ibm_watson.md) - [Kimi (Moonshot)](https://docs.rocketride.ai/nodes/llm_kimi.md): A component that connects to Moonshot AI's Kimi large language models for advanced natural language processing. - [MiniMax](https://docs.rocketride.ai/nodes/llm_minimax.md): A component that connects to MiniMax's large language models for advanced natural language processing. - [Mistral AI](https://docs.rocketride.ai/nodes/llm_mistral.md): A component that connects to Mistral AI's advanced language models for natural language processing. - [Ollama](https://docs.rocketride.ai/nodes/llm_ollama.md): A component that integrates with locally-hosted language models through Ollama. - [OpenAI](https://docs.rocketride.ai/nodes/llm_openai.md): A component that connects to OpenAI's latest GPT models for advanced natural language processing. - [OpenAI-Compatible API](https://docs.rocketride.ai/nodes/llm_openai_api.md): A component that connects to any OpenAI-compatible API endpoint for language model inference. - [Perplexity](https://docs.rocketride.ai/nodes/llm_perplexity.md): A component that connects to Perplexity AI's Sonar models for advanced natural language processing with real-time web search capabilities. - [Qwen](https://docs.rocketride.ai/nodes/llm_qwen.md): A component that connects to Alibaba Cloud's Qwen large language models via the DashScope API. - [Gemini Vision](https://docs.rocketride.ai/nodes/llm_vision_gemini.md): A component that connects to Google Gemini's vision-capable models for image analysis, OCR, visual understanding, and scene description. - [Mistral Vision](https://docs.rocketride.ai/nodes/llm_vision_mistral.md): A component that connects to Mistral AI's vision-capable models for image analysis, OCR, and visual understanding tasks. - [Ollama Vision](https://docs.rocketride.ai/nodes/llm_vision_ollama.md): A component that connects to locally-hosted open-source vision models through Ollama for image analysis, description, and visual understanding tasks. - [OpenAI Vision](https://docs.rocketride.ai/nodes/llm_vision_openai.md): A component that connects to OpenAI's vision-capable models for image analysis, OCR, visual understanding, and scene description. - [xAI](https://docs.rocketride.ai/nodes/llm_xai.md): A component that integrates with xAI's Grok language models for intelligent text generation and analysis. - [Local Text Output](https://docs.rocketride.ai/nodes/local_text_output.md): A target component that writes data to the file system. - [Media Toolkit: Inspect](https://docs.rocketride.ai/nodes/media_inspect.md): Measure streamed media and extract selected images. - [Memory (Internal)](https://docs.rocketride.ai/nodes/memory_internal.md): Run-scoped keyed memory store exposed as agent tools. - [Persistent Memory](https://docs.rocketride.ai/nodes/memory_persistent.md): A persistent cross-session memory node that retains data across pipeline invocations. - [Named Entity Recognition](https://docs.rocketride.ai/nodes/ner.md): A text processing component that identifies and extracts named entities from text using state-of-the-art transformer models. - [Normalize Facts](https://docs.rocketride.ai/nodes/normalize_facts.md): A deterministic fact normalizer for the audit-grade financial extraction suite. - [OCR](https://docs.rocketride.ai/nodes/ocr.md): A component that extracts machine-readable text from images and scanned documents using optical character recognition. - [Parser](https://docs.rocketride.ai/nodes/parse.md): A document parsing component that extracts rich content from a wide variety of document types. - [Pose Estimation](https://docs.rocketride.ai/nodes/pose_estimation.md): Top-down human pose estimation using RTMPose (Apache-2.0) via the rtmlib ONNX wrapper. - [Code](https://docs.rocketride.ai/nodes/preprocessor_code.md): A specialized component designed to parse and tokenize source code. - [General Text](https://docs.rocketride.ai/nodes/preprocessor_langchain.md): A preprocessing component that segments large bodies of text into intelligently sized chunks for downstream processing. - [LLM](https://docs.rocketride.ai/nodes/preprocessor_llm.md): A processing component that analyzes document content to extract concise summaries, key points, and named entities and to divide a document for storage into a vector database. - [Prompt](https://docs.rocketride.ai/nodes/prompt.md): A transformation component that takes multiple inputs and merges them into a single question with a configurable prompt. - [Question](https://docs.rocketride.ai/nodes/question.md): A transformation component that takes input text and encapsulates it as a Question object without modification. - [Reducto](https://docs.rocketride.ai/nodes/reducto.md): A parsing component that uses Reducto to extract text and structured data from various document formats including PDFs, images, and other document types. - [Remote Processing](https://docs.rocketride.ai/nodes/remote.md): A transport component that forwards data to a remote machine or processing node. - [Cohere Rerank](https://docs.rocketride.ai/nodes/rerank_cohere.md): A reranking component powered by Cohere's Rerank API that improves search quality by reordering retrieved documents based on their relevance to a given query. - [Response](https://docs.rocketride.ai/nodes/response.md): A component that returns processed answers back to the requesting client. - [RocketRide Graph](https://docs.rocketride.ai/nodes/rocketride_graph.md): A RocketRide-managed graph database backed by PostgreSQL + Apache AGE. - [RocketRide SQL](https://docs.rocketride.ai/nodes/rocketride_sql.md): A RocketRide-managed relational database. - [RocketRide Vector](https://docs.rocketride.ai/nodes/rocketride_vector.md): A RocketRide-managed vector store backed by PostgreSQL + pgvector. - [Scan Cropper](https://docs.rocketride.ai/nodes/scan_cropper.md): Splits a scan that holds several photos - a photo album page, or a handful of prints laid on the platen - into one image per photo. - [Schema Validate](https://docs.rocketride.ai/nodes/schema_validate.md): A guard node for the audit-grade financial extraction suite. - [Web Scraper Source](https://docs.rocketride.ai/nodes/scraper_beautifulsoup.md): Run-once web scraping source built on BeautifulSoup. - [Exa Search](https://docs.rocketride.ai/nodes/search_exa.md): A direct Exa web search node. - [Hybrid Rerank](https://docs.rocketride.ai/nodes/search_hybrid.md): A hybrid search component that re-ranks documents already retrieved by an upstream vector store, fusing their vector score with a BM25 keyword score for improved ordering. - [Astra DB](https://docs.rocketride.ai/nodes/store_astra.md): A vector database component for Astra DB, enabling efficient storage and retrieval of vector embeddings. - [MongoDB Atlas](https://docs.rocketride.ai/nodes/store_atlas.md): A vector database component for MongoDB Atlas, enabling efficient storage and retrieval of vector embeddings using MongoDB's native vector search capabilities. - [Chroma](https://docs.rocketride.ai/nodes/store_chroma.md): A vector database component for Chroma, enabling efficient storage and retrieval of vector embeddings. - [Elasticsearch](https://docs.rocketride.ai/nodes/store_elasticsearch.md): A vector database component for Elasticsearch, enabling efficient storage and retrieval of vector embeddings. - [Elasticsearch](https://docs.rocketride.ai/nodes/store_elasticsearch/elasticsearch.md): A vector database component for Elasticsearch, enabling efficient storage and retrieval of vector embeddings. - [OpenSearch](https://docs.rocketride.ai/nodes/store_elasticsearch/opensearch.md): An OpenSearch node that supports classic BM25 search and vector search for ingestion and retrieval workflows. - [Milvus](https://docs.rocketride.ai/nodes/store_milvus.md): A vector database component for Milvus, enabling efficient storage, indexing, and retrieval of vector embeddings. - [Pinecone](https://docs.rocketride.ai/nodes/store_pinecone.md): A component that connects to the Pinecone vector database for storing and retrieving high-dimensional embeddings. - [PostgreSQL (pgvector)](https://docs.rocketride.ai/nodes/store_postgres.md): A component that enhances PostgreSQL with vector similarity search capabilities through the pgvector extension. - [Qdrant](https://docs.rocketride.ai/nodes/store_qdrant.md): A vector database component for Qdrant, enabling efficient storage and retrieval of vector embeddings. - [Weaviate](https://docs.rocketride.ai/nodes/store_weaviate.md): A component that stores vector embeddings in a Weaviate instance for semantic search and retrieval. - [Summarization: LLM](https://docs.rocketride.ai/nodes/summarization.md): A processing component that analyzes document content to extract concise summaries, key points, and named entities. - [Telegram Bot](https://docs.rocketride.ai/nodes/telegram.md): A Telegram Bot source node that receives messages from users via the Telegram Bot API. - [Text Output](https://docs.rocketride.ai/nodes/text_output.md): A target component that writes data to the file system. - [Thumbnail](https://docs.rocketride.ai/nodes/thumbnail.md): A processing component that creates thumbnails from input images. - [Apify](https://docs.rocketride.ai/nodes/tool_apify.md): Exposes Apify Actors as agent tools. - [Bland AI](https://docs.rocketride.ai/nodes/tool_bland_ai.md): Make and manage AI-powered phone calls via Bland AI. - [Chart (Chart.js)](https://docs.rocketride.ai/nodes/tool_chartjs.md): Generates Chart.js v4 chart configurations from data using the pipeline LLM. - [Cognee](https://docs.rocketride.ai/nodes/tool_cognee.md): Persistent semantic memory backed by a Cognee server, exposed as three agent tools. - [Crustdata](https://docs.rocketride.ai/nodes/tool_crustdata.md): Exposes Crustdata's B2B company and people search as agent tools. - [Daytona](https://docs.rocketride.ai/nodes/tool_daytona.md): Gives agents an isolated Daytona cloud sandbox for running code and shell commands. - [DeepL](https://docs.rocketride.ai/nodes/tool_deepl.md): Exposes DeepL translation and AI rephrasing as agent tools. - [Exa Search](https://docs.rocketride.ai/nodes/tool_exa_search.md): Exposes Exa semantic web search as an agent tool. - [File Store Source](https://docs.rocketride.ai/nodes/tool_filesystem.md): File Store source. - [Firecrawl](https://docs.rocketride.ai/nodes/tool_firecrawl.md): Exposes Firecrawl web-scraping operations as agent tools. - [Google Cloud Storage](https://docs.rocketride.ai/nodes/tool_gcs.md): A tool component that interacts with Google Cloud Storage buckets. - [Git](https://docs.rocketride.ai/nodes/tool_git.md): Exposes local Git repository operations as agent tools. - [GitHub](https://docs.rocketride.ai/nodes/tool_github.md): Exposes GitHub repository operations as agent tools. - [GoHighLevel](https://docs.rocketride.ai/nodes/tool_gohighlevel.md): Exposes the GoHighLevel (LeadConnector) v2 REST API as agent tools. - [Google Calendar](https://docs.rocketride.ai/nodes/tool_google_workspace.md): Exposes Google Calendar operations as agent tools. - [Calendar](https://docs.rocketride.ai/nodes/tool_google_workspace/calendar.md): Exposes Google Calendar operations as agent tools. - [Docs](https://docs.rocketride.ai/nodes/tool_google_workspace/docs.md): Exposes Google Docs operations as agent tools. - [Drive](https://docs.rocketride.ai/nodes/tool_google_workspace/drive.md): Exposes Google Drive operations as agent tools. - [Gmail](https://docs.rocketride.ai/nodes/tool_google_workspace/gmail.md): Exposes Gmail operations as agent tools. - [Sheets](https://docs.rocketride.ai/nodes/tool_google_workspace/sheets.md): Exposes Google Sheets operations as agent tools. - [Guild.ai](https://docs.rocketride.ai/nodes/tool_guild.md): Run Guild.ai agents from a RocketRide pipeline or an agent. - [HTTP Request](https://docs.rocketride.ai/nodes/tool_http_request.md): Makes HTTP requests to public API endpoints, like curl for agents. - [LaserData Memory](https://docs.rocketride.ai/nodes/tool_laserdata_memory.md): Durable, shared agent memory exposed as tools, backed by LaserData (Apache Iggy) via the Laser SDK. - [Masky](https://docs.rocketride.ai/nodes/tool_masky.md): Masky AI avatars that speak, plus scene video, images and live conversations. - [MCP Client](https://docs.rocketride.ai/nodes/tool_mcp_client.md): Connects to the Butterbase MCP server and exposes its backend tools for agent tool-calling. - [Mem0](https://docs.rocketride.ai/nodes/tool_mem0.md): Long-term, shared agent memory exposed as tools, backed by the hosted Mem0 Platform. - [Excel](https://docs.rocketride.ai/nodes/tool_microsoft_365.md): Exposes Microsoft Excel operations as agent tools. - [Excel](https://docs.rocketride.ai/nodes/tool_microsoft_365/excel.md): Exposes Microsoft Excel operations as agent tools. - [Onedrive](https://docs.rocketride.ai/nodes/tool_microsoft_365/onedrive.md): Exposes Microsoft OneDrive operations as agent tools. - [Outlook Calendar](https://docs.rocketride.ai/nodes/tool_microsoft_365/outlook_calendar.md): Exposes Microsoft Outlook Calendar operations as agent tools. - [Outlook Mail](https://docs.rocketride.ai/nodes/tool_microsoft_365/outlook_mail.md): Exposes Microsoft Outlook Mail operations as agent tools. - [Word](https://docs.rocketride.ai/nodes/tool_microsoft_365/word.md): Exposes Microsoft Word document operations as agent tools. - [n8n](https://docs.rocketride.ai/nodes/tool_n8n.md): Trigger n8n workflows from a RocketRide pipeline or an agent. - [Notion](https://docs.rocketride.ai/nodes/tool_notion.md): Exposes a Notion workspace (search, pages, databases) as agent tools. - [Oura](https://docs.rocketride.ai/nodes/tool_oura.md): Exposes Oura Ring health data as read-only agent tools. - [Pipeline Tool](https://docs.rocketride.ai/nodes/tool_pipe.md): Exposes an inline pipeline as an agent tool. - [Pipedrive](https://docs.rocketride.ai/nodes/tool_pipedrive.md): Exposes the Pipedrive CRM REST API v1 as agent tools. - [Python](https://docs.rocketride.ai/nodes/tool_python.md): Executes Python code in a restricted in-process sandbox via exec(). - [Skills](https://docs.rocketride.ai/nodes/tool_skills.md): Gives agents custom skills: instructions for one kind of task, in the SKILL.md format. - [Slack](https://docs.rocketride.ai/nodes/tool_slack.md): Exposes Slack workspace operations as agent tools. - [Tavily](https://docs.rocketride.ai/nodes/tool_tavily.md): Exposes Tavily real-time web search as an agent tool. - [Luxor Sandbox](https://docs.rocketride.ai/nodes/tool_tenki.md): Gives agents a disposable Luxor Sandbox Linux VM for running code and shell commands, editing files and working with git repositories. - [v0 by Vercel](https://docs.rocketride.ai/nodes/tool_v0.md): A component that connects to Vercel's v0 API to generate React + Tailwind CSS UI components from natural-language prompts. - [Vertex AI Vector Search](https://docs.rocketride.ai/nodes/tool_vertex_search.md): A processing component that interacts with Google Vertex AI Vector Search. - [xTrace Memory](https://docs.rocketride.ai/nodes/tool_xtrace_memory.md): Long-term, shared agent memory exposed as tools, backed by xTrace Memory Manager. - [TwelveLabs](https://docs.rocketride.ai/nodes/twelvelabs.md): Sends a video to TwelveLabs along with instructions and returns the generated text response. - [Video Composer](https://docs.rocketride.ai/nodes/video_composer.md): Stitches a sequence of image frames into an MP4 video using FFmpeg. - [Webhook](https://docs.rocketride.ai/nodes/webhook.md): A user interface component that provides a web-based chat experience. - [Chat](https://docs.rocketride.ai/nodes/webhook/chat.md): A user interface component that provides a web-based chat experience. - [Drag & Drop](https://docs.rocketride.ai/nodes/webhook/dropper.md): A user interface component that provides a web-based dropper experience. - [Tools](https://docs.rocketride.ai/nodes/webhook/tools.md): A source component that transfers no data: it exists to host tool nodes. - [Webhook](https://docs.rocketride.ai/nodes/webhook/webhook.md): A source component that listens for incoming HTTP requests and accepts uploaded documents or data from external systems or processes. ## Connect - [CLI Reference](https://docs.rocketride.ai/connect/cli.md): The rocketride command-line tool sets up a workspace, starts pipelines, streams files, manages the file store, and deploys pipelines and apps from a terminal. - [HTTP MCP Server](https://docs.rocketride.ai/connect/mcp/http.md): The RocketRide engine has a built-in MCP server. Connect an AI assistant and it can build, validate, run, and observe pipelines and manage deployments. - [Connect a Client](https://docs.rocketride.ai/connect/mcp/http/connect.md): The endpoint is the same for every client. - [Resources & Widgets](https://docs.rocketride.ai/connect/mcp/http/resources-and-widgets.md): Beyond the tools, the RocketRide MCP server exposes two read-only resources for live engine state and renders some tool results as interactive widgets. - [Self-hosting](https://docs.rocketride.ai/connect/mcp/http/self-hosting.md): Every RocketRide engine serves the MCP endpoint automatically, with nothing extra to install or start. Find the URL for a self-hosted engine. - [Tools](https://docs.rocketride.ai/connect/mcp/http/tools.md): The RocketRide MCP server exposes 33 tools, 32 on a deployed engine where send_files is not offered. This page is the full tool reference. - [RocketRide MCP Server](https://docs.rocketride.ai/connect/mcp/stdio.md): Let AI assistants run your RocketRide pipelines via the Model Context Protocol. - [n8n](https://docs.rocketride.ai/connect/n8n.md): RocketRide and n8n connect in both directions. - [WebSocket protocol](https://docs.rocketride.ai/connect/websocket.md): The RocketRide engine speaks a native WebSocket protocol. - [WebSocket Events](https://docs.rocketride.ai/connect/websocket/observability.md): RocketRide exposes runtime observability (task lifecycle, periodic status, resource metrics, and per-component flow traces) as a live event stream over the… ## Deploy & Operate - [Choose How to Run RocketRide](https://docs.rocketride.ai/operate.md): One engine, two ways to run it: point your clients at managed RocketRide Cloud, or run the engine yourself. The same .pipe file runs on either. - [Cloud](https://docs.rocketride.ai/operate/cloud.md): RocketRide Cloud is a managed engine: the same runtime you can self-host, operated for you. Point a client at the Cloud endpoint and start building. - [Cloud Databases](https://docs.rocketride.ai/operate/cloud-databases.md): RocketRide Cloud runs PostgreSQL databases for its built-in database nodes, so a pipeline can keep data without a database of its own. - [Security](https://docs.rocketride.ai/operate/security.md): An overview of how RocketRide handles credentials, network exposure, and authentication across its components. - [Self-hosting](https://docs.rocketride.ai/operate/self-hosting.md): Run the RocketRide engine on your own machine when you want full control over where data and model calls go. It is the same engine that powers Cloud. - [Run the Engine in Docker](https://docs.rocketride.ai/operate/self-hosting/docker.md): The RocketRide engine ships as a published container image, the same one the VS Code extension Docker mode pulls. Run it with Docker in one command. - [Deploy on Kubernetes](https://docs.rocketride.ai/operate/self-hosting/kubernetes.md): The repository ships a Helm chart for clustered deployments: a deployment, service, config and secret handling, HPA, and ingress, linted and validated in CI. - [Production](https://docs.rocketride.ai/operate/self-hosting/production.md): Guidance for running the RocketRide engine as a production workload. Deployment topology is the load-bearing decision today. ## Reference - [Glossary](https://docs.rocketride.ai/reference/glossary.md): Terms used across the RocketRide docs. - [Pipeline JSON Reference](https://docs.rocketride.ai/reference/pipeline-reference.md): A .pipe file is JSON conforming to the interfaces below. ## Support & Community - [Contributing](https://docs.rocketride.ai/support/contributing.md): RocketRide is MIT licensed and developed in the open at rocketride-org/rocketride-server. There are more ways in than writing C++, so pick the one that fits. - [FAQ / Get Help](https://docs.rocketride.ai/support/get-help.md): Support questions opened as issues get converted to Discussions, so starting there is faster. Find where to ask questions and report problems. - [Release Notes](https://docs.rocketride.ai/support/release-notes.md): What shipped in each RocketRide release, generated from GitHub releases. - [Security Policy](https://docs.rocketride.ai/support/security-policy.md): RocketRide is open source and developed in the open with a documented security process. This page summarizes it; the policy is SECURITY.md in the repository. - [Troubleshooting](https://docs.rocketride.ai/support/troubleshooting.md): Common issues when building and running pipelines, and how to fix them.