airweave-ai/airweave

Features

• AI Knowledge Bases - Provides an AI knowledge base that syncs data from external APIs into a searchable layer for retrieval-augmented generation.
• Hybrid Search Retrievers - Combines semantic, neural, and keyword search via Reciprocal Rank Fusion for grounded results.
• Agentic Search Tools - Deploys an AI agent that iteratively explores data hierarchies and refines retrieval results using language models.
• Content Hierarchy Navigators - Searches a knowledge base by iteratively exploring, reading, and navigating content hierarchies.
• Collection Listings - Retrieves all knowledge collections for an organization with pagination and text search filtering.
• Model Context Protocol Servers - Runs a stateless HTTP or local stdio server for AI clients to search synced data via the Model Context Protocol.
• Retrieval Strategies - Adjusts search behavior by selecting hybrid, neural, or keyword retrieval and toggling query expansion and reranking.
• AI-Powered Answer Generation - Returns a natural language answer derived from the most relevant documents in a collection.
• Synced Data Searchers - Lets AI assistants search across synced data from external APIs using the Model Context Protocol.
• LLM-Driven Strategy Selectors - Uses an LLM to analyze the query and generate an optimized search strategy as a sensible default.
• Knowledge Collection Creators - Creates containers for organizing and searching data from multiple external sources.
• Data Connectors - Provides a catalog of pre-built data source connectors with authentication and configuration details.
• Multi-Source Collection Creators - Creates containers that organize and search data from multiple external sources.
• CRM Entity Schema Retrievals - Pulls accounts, contacts, deals, and invoices with full field schemas from CRM platforms.
• Scheduled External API Syncs - Connects to external apps, authenticates, extracts data, and performs incremental updates.
• Content Syncs - Synchronizes Confluence content into a unified searchable knowledge base for AI agents.
• Scheduled Sync Engines - Pulls data from external APIs using incremental updates and automated scheduling to keep the knowledge base current.
• Collection-Level Sync Schedulers - Configures automatic refresh schedules for collections of synced data sources.
• OneDrive Connectors - Retrieves files from OneDrive accounts via Microsoft Graph API for AI agent context retrieval.
• Collection Search Utilities - Searches across all data sources in a collection using semantic and keyword matching.
• Cross-Collection Search Engines - Queries a collection of multiple data sources with a single endpoint and returns ranked results.
• Natural Language Collection Queries - Provides natural-language search across synced data collections with AI-generated answers.
• Knowledge Collection Terminal Searchers - Searches knowledge collections from the terminal with vector, AI, and agentic modes.
• Dropbox Connectors - Connects to Dropbox to synchronize files and folder structures into a unified knowledge base.
• Custom Connector Development - Enables creating new integrations that pull data from external APIs and sync it into the knowledge base.
• Jira Connectors - Pulls projects, issues, and their relationships from Jira Cloud into a unified searchable knowledge base.
• Data Source Connections - Creates connections to external APIs using credentials, OAuth tokens, or auth providers.
• Content Syncs - Synchronizes Gmail threads, messages, and attachments into a unified searchable knowledge base.
• Incremental Sync Configurations - Tracks changes in external sources to re-sync only new or modified data, keeping the retrieval layer current.
• Content Syncs - Downloads and indexes files from Google Drive into a unified searchable knowledge base.
• Connection Listings - Retrieves all source connections for an organization with essential display fields.
• Live Data Source Connectors - Creates authenticated connector instances linked to specific accounts or workspaces for continuous data synchronization.
• Source Connection Adders - Attaches external data sources to collections with credentials and initial sync.
• Source Connection Sync Triggers - Starts synchronization runs for source connections with full re-sync option.
• Incremental Sync Checkpointings - Uses cursor-based incremental sync to detect and sync only new or modified documents.
• Typed Schema Mappings - Maps source fields to typed Pydantic schemas for consistent searchable entity storage across diverse APIs.
• Entity Search & Indexing - Indexes extracted items as searchable entities and returns results optimized for LLM consumption.
• Grounded Context Retrieval - Returns facts from the original data source at query time so agents use verified information.
• Hybrid Search - Combines semantic and keyword search via Reciprocal Rank Fusion to deliver balanced relevance.
• Metadata Filtering - Restricts results to content matching user-defined metadata conditions, with filters enforced across all search tiers.
• Metadata Search Engines - Applies user-defined metadata filters that are AND'd into every search, acting as hard constraints across all search tiers.
• Cross-Docset Searching - Enables AI agents to search across all synced apps and databases using natural language queries.
• Knowledge Collection Metadata Retrievers - Fetches configuration, sync settings, and metadata for knowledge collections.
• Unified Multi-Source Queries - Searches across entities from multiple connected sources in a single collection.
• Tiered Search Configurations - Offers three search tiers — instant, classic, and agentic — that trade speed for result quality and reasoning depth.
• Unified Data Searches - Connects to multiple external tools and exposes their data through a single search interface for AI agents.
• Context Search Retrievers - Returns search results optimized for LLM consumption with source attribution and original content links.
• Search Result Filtering - Narrows search results using structured conditions on metadata fields, combined with AND/OR logic.
• Continuous Sync Engines - Keeps the knowledge base current by automatically pulling updates from connected sources without manual intervention.
• MCP Server Integrations - Connects AI assistants to a knowledge base via the Model Context Protocol for natural-language search.
• Custom Data Source Implementations - Provides a framework for writing source classes that authenticate, fetch, and yield structured entities.
• HubSpot Syncs - Synchronizes HubSpot CRM entities into a unified searchable knowledge base for AI agents.
• GitHub Syncs - Synchronizes GitHub repository data into a unified searchable knowledge base for AI agents.
• Data Connector Libraries - Ships a comprehensive library of pre-built data connectors for CRM, productivity, and communication tools.
• Entity Hierarchy Navigators - Deploys an AI agent that iteratively searches, reads full documents, and navigates entity hierarchies.
• Third-Party Service Integrations - Provides pre-built integration code for connecting to external APIs with authentication and data sync.
• Webhook Registrations - Creates subscriptions that send POST requests to user-defined URLs when specified lifecycle events occur.
• Data Sync Job Launchers - Provides API endpoints to manually trigger data sync jobs on source connections.
• Unified Data Models - Maps source-specific data structures into a standardized entity format for consistent querying.
• OAuth Token Injections - Ships OAuth token injection to skip consent screens when creating new source connections.
• External Authentication - Handles OAuth flows, API keys, and database credentials to connect to external data sources.
• Multi-Method API Authentication - Supports OAuth 2.0, API keys, and credentials to securely connect to a wide range of external sources.
• OAuth 2.0 Authorization Flows - Redirects users to a service provider's consent screen to authorize access without manual token management.
• Authorization Gateways - Manages third-party authorizations through browser flows, token injection, and enterprise SSO for secure connections.
• OAuth Authentication - Uses browser-based OAuth flow, token injection, or enterprise SSO to securely connect with Slack.
• Google OAuth Providers - Configures OAuth 2.0 credentials and scopes to connect with Google Workspace APIs for data retrieval.
• OAuth2 Providers - Uses OAuth 2.0 to authorize access to Salesforce data without exposing user credentials.
• Data Schema Definitions - Creates Pydantic schemas that map source fields to searchable content or downloadable files.
• Webhook Event Notifications - Pushes HTTP POST notifications to registered endpoints when sync, connection, or collection lifecycle events occur.
• Notion Integrations - Extracts databases, pages, and files from a Notion workspace into a unified searchable knowledge base.
• Source Management - Manages data sources and triggers syncs from the command line with interactive or JSON output.
• External Data Source Integrations - Pulls data from external applications, databases, and document stores by abstracting their unique APIs and authentication methods.
• Vector and Hybrid Searches - Performs direct vector or hybrid search against a collection and returns ranked results with metadata.
• Search Guidance Instructions - Teaches AI agents how to formulate queries, choose search parameters, interpret results, and synthesize answers from a knowledge base.
• Platform Skill Installers - Installs portable instruction files for AI agents to follow guided platform workflows.
• Custom Base URL Configurations - Allows setting a custom base URL for self-hosted instances in MCP settings.
• Transcript Syncs - Retrieves and indexes meeting transcripts from Fireflies.ai for unified search.
• Custom Server Connections - Points the search tool to a self-hosted or non-default server URL.
• Agent Response Streams - Emits real-time SSE events showing agent reasoning, tool calls, and intermediate results during search.
• SDK Context Retrievers - Queries the unified retrieval layer programmatically using Python or TypeScript SDKs.
• SDK Querying Tools - Searches collections and retrieves grounded context programmatically via client libraries.
• Google Calendar Synchronizations - Pulls calendars, events, and free/busy information from Google Calendar into a unified knowledge base.
• Presentation Content Extractors - Downloads PowerPoint files from OneDrive and SharePoint, extracts text, and indexes it for semantic search.
• Salesforce Syncs - Extracts Salesforce Accounts, Contacts, and Opportunities via REST API and indexes them for AI agent retrieval.
• Zoho Syncs - Syncs Zoho CRM accounts, contacts, deals, and invoices into a unified searchable knowledge base for AI agents.
• Content Syncs - Retrieves and indexes Google Docs content for full-text semantic search in a knowledge base.
• Meeting Syncs - Pulls Zoom meetings, participants, recordings, and transcripts into a unified searchable knowledge base.
• Context Search Integrations - Retrieves payment and financial data from Stripe through a unified search layer for AI agents.
• Financial Data Syncs - Pulls Stripe transactions, customers, and subscriptions into a unified searchable knowledge base for AI agents.
• Data Syncs - Synchronizes Microsoft Teams data into a unified searchable knowledge base for AI agents.
• SharePoint Connectors - Syncs SharePoint sites, document libraries, and files via Microsoft Graph API into a searchable knowledge base.
• Content Searchers - Makes SharePoint data searchable through a unified retrieval layer for AI agents and RAG systems.
• OneNote Syncs - Synchronizes OneNote notebooks and pages into a unified searchable knowledge base.
• Cloud Document Indexers - Downloads Word files from OneDrive and SharePoint, converts to markdown, and indexes for semantic search.
• Content Indexers - Indexes OneDrive files and folders into a unified searchable knowledge base for AI agents and RAG systems.
• Collection Metadata Inspection - Returns metadata and configuration information for specific knowledge collections.
• Zendesk - Connects to Zendesk instance and syncs tickets, comments, and users into a unified searchable knowledge base.
• Context Search Integrations - Makes Zendesk ticket fields, comments, and user profiles available through a unified search layer.
• Apollo CRM Syncs - Synchronizes contacts, accounts, sequences, and email activities from Apollo into a unified searchable knowledge base for AI agents and RAG systems.
• Asana Comment Syncs - Synchronizes comment data associated with Asana entities into a unified searchable knowledge base.
• Asana File Syncs - Synchronizes file attachments from Asana into a unified searchable knowledge base.
• Asana Project Syncs - Synchronizes project details such as status, due dates, notes, members, and custom fields into a unified searchable knowledge base.
• Asana Section Syncs - Synchronizes section metadata and project associations into a unified searchable knowledge base.
• Asana Task Syncs - Synchronizes task details including assignees, due dates, dependencies, and completion status into a unified searchable knowledge base.
• Attio CRM Syncs - Synchronizes objects, lists, records, and notes from Attio into a unified searchable knowledge base for AI agents and RAG systems.
• Bitbucket Syncs - Synchronizes workspaces, repositories, directories, and code files from Bitbucket into a unified searchable knowledge base for AI agents.
• Box Syncs - Synchronizes folders, files, comments, users, and collaborations from Box into a unified searchable knowledge base.
• Calendar Syncs - Synchronizes Outlook calendar events and attachments into a unified searchable knowledge base for AI agents.
• Coda Document Syncs - Synchronizes docs, pages, tables, and rows from Coda into a unified searchable knowledge base for AI agents.
• CRM Syncs - Syncs Pipedrive CRM records including persons, deals, and activities into a unified searchable knowledge base.
• E-Commerce Syncs - Syncs Shopify products, customers, orders, and inventory into a unified searchable knowledge base.
• Kanban Board Syncs - Syncs Trello boards, lists, cards, and checklists into a unified searchable knowledge base for AI agents.
• Linear Syncs - Synchronizes Linear project management data into a unified searchable index for AI agents.
• Mail Syncs - Pulls Outlook emails, folders, and attachments into a unified searchable knowledge base for AI agents.
• Task Management Syncs - Syncs Todoist projects, tasks, sections, and comments into a unified searchable knowledge base for AI agents.
• Full Re-sync Triggers - Provides a manual trigger to force a complete re-sync of all data from a connected source.
• Airtable Syncs - Synchronizes bases, tables, records, comments, and attachments from Airtable into a unified searchable knowledge base for AI agents.
• ServiceNow Data Searchers - Makes synced ServiceNow records searchable through a unified query layer for AI agents and RAG systems.
• Keyword Search - Returns only content containing exact query terms using BM25 text matching for precise lookups.
• ServiceNow Context Retrievers - Makes synced ServiceNow records searchable through a unified retrieval layer for AI agents and RAG systems.
• Source-Attributed Retrievals - Returns search results with breadcrumbs to original sources for traceable information.
• Collection Deletion - Permanently removes collections and all associated synced data and connections.
• Vector Similarity Search - Matches queries against stored content using dense vector cosine similarity for conceptual relevance.
• Platform Agent Setup Guides - Teaches AI agents how to use SDKs, create collections, and run searches on the platform.
• Context Retrieval Integrations - Queries synced Todoist data through a unified search layer to provide AI agents with task and project context.
• Knowledge Base Syncing - Connects to Slab workspace via GraphQL API and syncs topics, posts, and comments into a searchable knowledge base.
• Asana Workspace Syncs - Synchronizes workspace metadata including name, organization status, and email domains into a unified searchable knowledge base.
• Cal.com Booking Syncs - Pulls booking records from the Cal.com API, supporting incremental sync and pagination to keep the knowledge base current.
• ClickUp Workspace Syncs - Extracts and synchronizes workspaces, spaces, folders, lists, tasks, comments, and subtasks from ClickUp into a unified knowledge base.
• Document360 Syncs - Synchronizes Document360 knowledge base content into a unified searchable index for AI agents.
• Freshdesk Syncs - Synchronizes Freshdesk support data into a unified searchable knowledge base for AI agents.
• Intercom Syncs - Synchronizes Intercom conversations and tickets into a unified searchable knowledge base.
• ITSM Syncs - Syncs ServiceNow incidents, knowledge articles, and change requests into a unified searchable knowledge base.
• Collection Updaters - Updates collection display names and sync schedules without changing identifiers.
• Monday Syncs - Synchronizes Monday.com boards and items into a unified searchable index for AI agents.
• GitLab Syncs - Synchronizes GitLab project data into a unified searchable knowledge base for AI agents.
• SDK Client Initialization - Sets up the SDK with an API key and optional base URL to authenticate and communicate with the platform.
• Local MCP Server Launches - Launches the MCP server as a local stdio process for desktop AI clients.
• Post-Sync Workflow Triggers - Triggers downstream workflows in external systems after sync completion or failure.
• Search Block Workflow Connectors - Connects search block outputs to downstream workflow blocks for automated processing.
• MCP HTTP Servers - Runs the MCP server as a stateless HTTP service for cloud-based AI platforms.
• Hosted Deployments - Deploys the MCP server as a stateless HTTP endpoint for cloud AI platforms with per-request authentication.
• Self-Hosted Deployments - Points the MCP server at a self-hosted instance using local or Docker deployment for private infrastructure.
• Server-Sent Events - Delivers real-time reasoning streams and search progress updates via SSE for live agentic search.
• Cross-Channel Searchers - Returns results from every channel the user has access to, providing a unified view of Slack messages.
• Message Data Retrieval - Returns structured message fields from Slack search results for AI agent consumption.
• Real-Time Search Integrations - Queries Slack's search API in real time and merges results with other sources for unified retrieval.
• External Source Credential Schemas - Specifies credential types and schemas required to connect to external systems via API keys, OAuth2, or database connections.
• Webhook Signature Verifiers - Validates HMAC-SHA256 signatures on incoming payloads to confirm origin and integrity.
• Pre-Configured Hosted Flows - Authenticates users through a pre-configured, hosted OAuth flow that handles the entire process automatically.
• Slack OAuth Integrations - Authenticates with Slack using OAuth 2.0 through the UI or API, supporting browser flows, tokens, and enterprise SSO.
• Webhook Security - Validates cryptographic signatures on incoming webhook requests to confirm origin authenticity.
• Database Property Indexers - Structures Notion database properties and their values as searchable entities with formatted display values.
• Clinical Trial Content Fetchers - Connects to the AACT PostgreSQL database to extract clinical trial records and create web entities linking to ClinicalTrials.gov pages.
• Search Tool Integrations - Integrates a search tool into Vercel AI SDK workflows for querying a unified knowledge base.
• HTTP Event Subscription - Receives real-time notifications for domain-specific events such as sync completions or failures via HTTP POST.
• Search Result Workflow Passers - Passes search results and AI answers to downstream workflow blocks for further processing.
• Widget Embedding - Provides an iframe-based modal widget for OAuth flows, credential forms, and connection management.

Star history