awesome-repositories.com
Blog
MCP
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetServeur MCPÀ proposNotre méthodologiePresse
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
airweave-ai avatar

airweave-ai/airweave

0
View on GitHub↗
6,453 stars·811 forks·Python·MIT·18 vuesairweave.ai↗

Airweave

Airweave is a unified AI knowledge base platform that syncs data from external APIs into a searchable layer for retrieval-augmented generation. It provides a pre-built data connector library and a framework for building custom connectors, enabling the extraction, transformation, and synchronization of structured and unstructured data from SaaS applications. The platform includes a hybrid vector retrieval system that combines semantic, neural, and keyword search strategies to deliver grounded context for AI agents.

The platform distinguishes itself through an agentic search engine that iteratively explores data hierarchies and refines results using language models, alongside an OAuth integration gateway that manages third-party authorizations through browser flows, token injection, and enterprise SSO. It offers a Model Context Protocol server that can be deployed as a stateless HTTP service or local stdio process, enabling AI assistants to search synced data. The system also includes a webhook event notification system that pushes HTTP POST notifications for sync, connection, and collection lifecycle events with automatic retries and signature verification.

The platform supports a wide range of capabilities including connection management with an embedded iframe-based widget, CLI and SDK tools for programmatic access, configurable sync scheduling with incremental updates, and multiple retrieval strategies such as hybrid, keyword, vector, and agentic search. It provides search result filtering with metadata conditions, real-time streaming via Server-Sent Events, and AI-generated answer derivation from relevant documents. The platform also includes auditing, monitoring, and rate limiting features, along with support for self-hosted deployments and custom instance configuration.

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.

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI
  • 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.

    • Historique des stars

    Graphique de l'historique des stars pour airweave-ai/airweaveGraphique de l'historique des stars pour airweave-ai/airweave

    Alternatives open source à Airweave

    Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec Airweave.
    • nangohq/nangoAvatar de NangoHQ

      NangoHQ/nango

      10,772Voir sur GitHub↗

      Nango is an open-source platform that connects applications to external APIs by managing authentication, data synchronization, and custom function execution. It provides a managed runtime for TypeScript integration functions, handling OAuth flows, credential storage, and token refresh for hundreds of external APIs while keeping secrets isolated from application code. The platform distinguishes itself by exposing integration functions as discoverable tools for AI agents through an MCP server or API, with per-user credential isolation that keeps provider secrets out of the agent loop. It offers

      TypeScriptaccess-tokenapiapi-client
      Voir sur GitHub↗10,772
    • unstructured-io/unstructuredAvatar de Unstructured-IO

      Unstructured-IO/unstructured

      14,019Voir sur GitHub↗

      Unstructured is an enterprise-grade data orchestration engine designed to transform raw, unstructured files into structured, machine-readable formats. It functions as a comprehensive platform for document ingestion, partitioning, and enrichment, specifically engineered to prepare complex data for retrieval-augmented generation and agentic AI workflows. The platform distinguishes itself through its sophisticated document processing strategies, which combine rule-based extraction with vision-language models to handle diverse file layouts, tables, and images. It provides a modular architecture t

      HTMLdata-pipelinesdeep-learningdocument-image-analysis
      Voir sur GitHub↗14,019
    • lancedb/lancedbAvatar de lancedb

      lancedb/lancedb

      9,031Voir sur GitHub↗

      LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector search engine. It serves as a high-performance backend for indexing and retrieving high-dimensional embeddings, providing the foundation for machine learning data pipelines. The system distinguishes itself through a combination of cloud-native object storage and immutable version tracking, allowing for data time-travel and reproducible AI experiments. It integrates hybrid search capabilities, merging dense vector similarity with BM25 full-text search and SQL-like scalar filters

      HTMLapproximate-nearest-neighbor-searchimage-searchnearest-neighbor-search
      Voir sur GitHub↗9,031
    • discord/discord-api-docsAvatar de discord

      discord/discord-api-docs

      6,425Voir sur GitHub↗
      MDXdiscorddiscord-apidiscordapp
      Voir sur GitHub↗6,425
    Voir les 30 alternatives à Airweave→

    Questions fréquentes

    Que fait airweave-ai/airweave ?

    Airweave is a unified AI knowledge base platform that syncs data from external APIs into a searchable layer for retrieval-augmented generation. It provides a pre-built data connector library and a framework for building custom connectors, enabling the extraction, transformation, and synchronization of structured and unstructured data from SaaS applications. The platform includes a hybrid vector retrieval system that combines semantic, neural, and keyword search strategies…

    Quelles sont les fonctionnalités principales de airweave-ai/airweave ?

    Les fonctionnalités principales de airweave-ai/airweave sont : AI Knowledge Bases, Hybrid Search Retrievers, Agentic Search Tools, Content Hierarchy Navigators, Collection Listings, Model Context Protocol Servers, Retrieval Strategies, AI-Powered Answer Generation.

    Quelles sont les alternatives open-source à airweave-ai/airweave ?

    Les alternatives open-source à airweave-ai/airweave incluent : nangohq/nango — Nango is an open-source platform that connects applications to external APIs by managing authentication, data… unstructured-io/unstructured — Unstructured is an enterprise-grade data orchestration engine designed to transform raw, unstructured files into… lancedb/lancedb — LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector… discord/discord-api-docs. netease-youdao/qanything — QAnything is a retrieval-augmented generation application framework and self-hosted AI interface. It functions as a… drasi-project/drasi-platform — The platform is a distributed system designed for real-time data monitoring, continuous graph-based query processing,…