AI applications & RAG

AI application builders, chat interfaces, agents and retrieval-augmented generation.

8 listings, including 8 from other publishers. Entries cover the deployment options documented on their individual pages.

Watch this category with RSS · Build a requirements shortlist

Deployment comparison

ListingDocumented cloudsDeployment and infrastructureLicensingInstallationOperations and limitations
AnythingLLM DockerAWS, Google Cloud, RailwayCustomer-operated
Servers / containers
Open Source / Open Core

MIT License for upstream AnythingLLM; model weights, connectors and provider services have separate terms.

Run the official Docker edition on a customer-operated host with persistent application storage and configured model/vector endpoints.Customer manages users, documents, persistent storage, model access, integration secrets, backups and upgrades.
Scope and evidence

The Docker edition supports multi-user operation and differs from the desktop application. Local inference is an option; configured external LLMs, embeddings, vector stores and agent tools can send data outside the account. AnythingLLM v1.20.0 hardens embed history, extension API-key authorization, workspace-agent access, password recovery, framing, and document-tool downloads. Optional MCP identity forwarding creates a new outbound identity path; keep the server and extension on compatible 1.20+ versions.

  • AnythingLLM Docker installation overview — The project explicitly names AWS, Google Cloud and Railway for self-hosting the Docker edition, paired with its Docker installation workflow. This is an upstream hosting compatibility statement. Model endpoints, embeddings and external vector stores are separately configured and can have different data boundaries.

    Vendor / upstream documentation · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-12

Dify Self-HostedAlibaba CloudCustomer-operated
Servers / containers
Source Available

Modified Apache 2.0 terms; multi-workspace service operation and frontend branding can require commercial authorization.

Official Docker Compose deployment; pin a release and configure its required services.Customer operates the containers, persistent stores, secrets, backups and upgrades; commercial edition support varies.
Scope and evidence

Self-hosting Dify does not itself host every model used by a flow. Model-provider plugins, embedding services, tools and connectors may send inputs or retrieved content outside the deployment. Select local endpoints where required and review each dependency. This entry does not conflate the generic self-hosted stack with the separately licensed AWS Premium edition. Dify 1.20.0 changes deployment and API behavior: OPENAPI_ENABLED defaults to true, shared.env is retired, six migrations apply from 1.19, and HITL, plugin-daemon, OpenShell, and optional file-scanning requirements change. It also fixes OAuth callback reuse, member-role enforcement, vector deletion scope, public stream detail exposure, and CVE-2026-116591.

  • Dify Docker deployment on Alibaba Cloud ECS — Alibaba Cloud documents cloning upstream Dify and running its Docker deployment on a customer ECS instance. The example then integrates an MCP server; model providers and other outbound integrations must be reviewed separately.

    Provider guide · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Dify Community Edition full application on Alibaba Compute Nest — Alibaba documents a Dify Community Edition service instance that creates ECS compute in the customer-selected VPC, zone and region, then exposes the installed Dify application for administrator registration. This is application hosting rather than an MCP/model connector, and is separate from the licensed Dify AWS Premium offering. Review model endpoints and release compatibility.

    Provider guide · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-12

Langflow Self-HostedAWS, Azure, Google CloudCustomer-operated
Servers / containers
Open Source / Open Core

MIT for the upstream project; connected models, providers and bundles have their own terms.

Official Docker image or Docker Compose; Python installation and Kubernetes options are also documented.Customer manages the application, database, access controls, installed components, backups and version upgrades.
Scope and evidence

The reviewed model-component docs support Ollama and configurable OpenAI-compatible endpoints as well as commercial providers. External models, embeddings, tools or custom components can move data beyond the host. Hosting Langflow is distinct from hosting those dependencies and from any vendor-managed service. Langflow 1.13.3 enforces custom-component policy in background workflows, invalidates native sessions after password changes, updates security dependencies, and aligns Docker and wheel packaging. Recheck custom components and session behavior after upgrading.

  • Langflow Kubernetes deployment architecture — The project explicitly identifies EKS, AKS and GKE for its Helm deployment. Separate the development IDE from the production runtime, and review PostgreSQL, model endpoints and external vector stores.

    Vendor / upstream documentation · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-12

LibreChat Self-HostedRailway, DigitalOceanCustomer-operated
Servers / containers
Open Source / Open Core

MIT

Official Railway one-click template or Docker on a DigitalOcean Ubuntu DropletCustomer manages the Railway project or DigitalOcean Droplet, application secrets, model credentials, data services, backups, scaling and upgrades. Railway operates its platform; Droplet users also maintain the operating system and Docker runtime.
Scope and evidence

The Railway path runs in the customer's project on platform-managed infrastructure; the DigitalOcean path uses a customer-operated Droplet. External model, embedding, search and tool providers receive data according to customer configuration. Review generated secrets, public networking, persistent data services and image updates before production use.

  • LibreChat one-click deployment on Railway — LibreChat documents creating a Railway account, reviewing the template's three containers and environment variables, deploying the services and accessing the resulting LibreChat URL in the customer's Railway project.

    Vendor / upstream documentation · Reviewed 2026-11-15. Vendor support commitment: not assessed; confirm the selected release and contract.

  • LibreChat deployment on DigitalOcean — The upstream guide creates an Ubuntu Droplet in the customer DigitalOcean project, configures a user and firewall, then links to the Docker installation steps. The example is for a small personal deployment, not a production sizing guarantee.

    Vendor / upstream documentation · Reviewed 2026-11-15. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-15

MaxKB Community EditionAlibaba CloudCustomer-operated
Servers / containers
Open Source / Open Core

GNU General Public License version 3 for Community Edition. Professional and Enterprise editions add separately licensed features and support.

Create the documented MaxKB Community Edition service instance through Alibaba Cloud Compute Nest, or use the publisher-documented Alibaba Cloud Marketplace image on a customer ECS server.Customer manages the ECS host, VPC and security-group exposure, administrator credentials, persistent PostgreSQL data, backups, upgrades, capacity and credentials for model and tool integrations.
Scope and evidence

The Compute Nest deployment requires RAM permissions with full access to ECS, VPC and ROS plus Compute Nest user access; review and reduce deployment privileges after provisioning where practical. Community Edition is single-tenant, x86-64 only and supports single-node or cold-standby deployment rather than Enterprise clustering. RBAC, SSO, audit logs, open API access, conversation-user authorization and several enterprise integrations are reserved for paid editions. Current upstream v2 installation guidance calls for at least 4 CPU cores, 8 GB RAM and 100 GB of disk, exposes the web service on port 8080 and supplies default administrator credentials that must be changed immediately. The publisher recommends offline installation for production and requires a database backup before upgrades. Public or separately hosted model, embedding, reranking and tool providers can receive application data even when MaxKB itself runs in the customer account. The current upstream v2 container image and persistence paths differ from the legacy English guide; check the release packaged by the cloud installer before applying upstream configuration or upgrades. MaxKB v2.10.9-lts fixes multiple cross-workspace access and deletion flaws, stored XSS with account-takeover impact, custom-tool secret exposure, SSRF paths including possible cloud-credential theft, anonymous provider API-key disclosure and unauthorized conversation or knowledge-base access. Upgrade the LTS line and retest workspace, tool and provider boundaries.

  • MaxKB Community Edition service instance in Alibaba Compute Nest — Alibaba Cloud documents creation of a MaxKB Community Edition service instance in a customer-selected region, zone, VPC and VSwitch using customer-selected ECS capacity and billing. The deployed application is reached through the ECS public address on port 8080. The workflow requires broad ECS, VPC, ROS and Compute Nest permissions and returns default administrator credentials that must be changed.

    Provider guide · Reviewed 2026-11-16. Vendor support commitment: not assessed; confirm the selected release and contract.

  • MaxKB image deployment from Alibaba Cloud Marketplace — The publisher documents selecting the MaxKB image while purchasing an Alibaba Cloud server, starting the image and opening port 8080 in the customer's security group. It recommends at least 4 CPU cores and 8 GB RAM and instructs administrators to replace the default password after first login.

    Vendor / upstream documentation · Reviewed 2026-11-16. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-16

Onyx Self-HostedAWS, Azure, Google Cloud, DigitalOceanCustomer-operated
Servers / containers
Open Source / Open Core

MIT Community Edition; Business and Enterprise features use separate commercial terms.

Docker Compose on a VM or official Kubernetes and Terraform deploymentCustomer manages application services, databases, search, object storage, connectors, model credentials, backups, scaling and upgrades.
Scope and evidence

This entry covers self-hosted Onyx, not a vendor-hosted environment. External LLM, embedding and connector services receive data according to the customer's configuration. Business and Enterprise features and support require separate commercial entitlements.

  • Onyx on AWS — Onyx documents self-hosting on a customer EC2 instance and links a production EKS architecture using AWS managed dependencies.

    Vendor / upstream documentation · Reviewed 2026-11-14. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Onyx on Azure — Onyx documents self-hosting on an Azure VM and an AKS Terraform path using customer Azure managed services.

    Vendor / upstream documentation · Reviewed 2026-11-14. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Onyx on Google Cloud — Onyx documents Compute Engine and production GKE deployment paths in the customer's Google Cloud project.

    Vendor / upstream documentation · Reviewed 2026-11-14. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Onyx on DigitalOcean — Onyx documents installing its self-hosted stack on a customer DigitalOcean Droplet.

    Vendor / upstream documentation · Reviewed 2026-11-14. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-14

Open WebUI Self-HostedAWS, Azure, Google CloudCustomer-operated
Servers / containers
Source Available

Open WebUI license based on BSD-style terms with additional branding restrictions and defined exceptions; enterprise terms may be required for rebranding.

Official Docker image, Python installation or Kubernetes deployment.Customer runs application storage, authentication, provider configuration, updates and backups.
Scope and evidence

The UI sends messages to the model endpoint selected for a conversation. Local Ollama or vLLM endpoints can keep inference on customer infrastructure; cloud APIs, embeddings, tools and plugins have separate data flows. The current license restricts branding removal in larger deployments, with small-deployment, permission and enterprise-license exceptions; review the actual terms. Open WebUI v0.13.4 replaces Direct Connections and Integrations with Tether and migrates image settings. Deployments using Terminals server connections require Terminals 0.4.0 or later; upgrading that server from 0.3.x requires manual migration. Open Terminal and Tether terminal connections are unaffected by this migration. Tether introduces user-device and local-command paths that require explicit trust review.

  • Open WebUI deployment on AWS ECS / Fargate — Project deployment instructions cover the application on AWS ECS / Fargate with external database, Redis and file storage. Model inference is separate; review model endpoints, egress and WebSocket/runtime limits.

    Vendor / upstream documentation · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Open WebUI deployment on Azure Container Apps — Project deployment instructions cover the application on Azure Container Apps with external database, Redis and file storage. Model inference is separate; review model endpoints, egress and WebSocket/runtime limits.

    Vendor / upstream documentation · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Open WebUI deployment on Google Cloud Run — Project deployment instructions cover the application on Google Cloud Run with external database, Redis and file storage. Model inference is separate; review model endpoints, egress and WebSocket/runtime limits.

    Vendor / upstream documentation · Reviewed 2026-11-12. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-12

RAGFlowAWS, Azure, Google Cloud, Alibaba Cloud, RailwayCustomer-operated
Servers / containers
Open Source / Open Core

Apache License 2.0 for upstream RAGFlow; models, data assets and dependencies retain their own terms.

Versioned upstream Docker Compose, provider-specific VM packages or community deployment templates; select a path compatible with the intended RAGFlow release.Customer manages document storage, indexing, app services, access controls, model endpoints, backups and upgrades.
Scope and evidence

Deployment options include customer AWS, Azure and Google Cloud infrastructure, Alibaba Compute Nest, and a Railway project. The evidence trail identifies the publishers and template versions. Hosting RAGFlow does not automatically self-host its LLM, embeddings or reranker; choose private or local model endpoints where required.

  • Community RAGFlow deployment on AWS ECS Fargate through stdapi.ai — The sample provisions the RAGFlow application and workers, OpenSearch, Aurora PostgreSQL, Valkey, S3 and a Bedrock gateway in the customer AWS account. Source inspection confirms the v0.26.4 Python image pin; it does not establish compatibility with the 1.0 Go rewrite. This community integration also requires the separately billed stdapi.ai gateway and Bedrock access. Review its documented networking, client-security, availability and cost limitations before use.

    Community template · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted · Version: 0.26.4. Vendor support commitment: not assessed; confirm the selected release and contract.

  • cloudimg RAGFlow Azure VM deployment and operations guide — The image publisher documents an Azure VM in the customer subscription running the complete Compose stack, including Elasticsearch, MySQL, MinIO, Redis and a local embedding service. Its guide pins RAGFlow v0.26.4, not 1.0. This is a third-party repackaged image with additional support charges, not an upstream-endorsed distribution. Confirm image access, current patch/migration requirements, TLS configuration and the separately configured chat-model endpoint.

    Third party package · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted · Version: 0.26.4. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Techlatest RAGFlow VM deployment in a customer Google Cloud project — The image publisher documents selecting the customer project, deployment service account, zone, network and Compute Engine VM, then completing RAGFlow initialization and configuring its bundled Ollama models. This is a third-party packaged deployment; the guide does not establish a specific current RAGFlow release or 1.0 compatibility. Confirm the image version, support charges, model licenses, resource sizing and network exposure before use.

    Third party package · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted. Vendor support commitment: not assessed; confirm the selected release and contract.

  • RAGFlow Community deployment on Alibaba Cloud Compute Nest — Alibaba Cloud documents provisioning a RAGFlow Community service instance with customer ECS, VPC and vSwitch parameters. This is distinct from the managed AI-Native Database Service integration. Review image version, access controls, model endpoints and the broad example RAM permissions before production.

    Provider guide · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Community RAGFlow Railway application stack — This community template deploys the application, Elasticsearch, MySQL, Redis, a local embedding service and object storage into the customer Railway project. Its linked Dockerfile pins upstream RAGFlow v0.27.1 with a Railway startup/configuration wrapper. The template is not proof of 1.0 compatibility or upstream support; review migrations and the separately configured chat-model endpoint. Railway manages the underlying infrastructure.

    Community template · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted · Version: 0.27.1. Vendor support commitment: not assessed; confirm the selected release and contract.

  • Railway deployment image source and release pin — Source inspection confirms the v0.27.1 base image and the custom configuration, nginx and startup wrapper used by the linked Railway template. The upstream 1.0 release changes the architecture and requires its documented migration path; do not substitute a new image tag without reviewing the complete stack.

    Community template · Reviewed 2026-11-12 · Scope: Community / upstream open-source; third-party distribution where noted · Version: 0.27.1. Vendor support commitment: not assessed; confirm the selected release and contract.

Cloud evidence reviewed 2026-11-12

Choose 2–4 listings to compare

Browse listing cards

How these listings fit

AnythingLLM Docker
Multi-user application for document-grounded chat, RAG and agents with configurable model and vector-database integrations.
Dify Self-Hosted
Visual application, agent-workflow and retrieval-augmented generation platform. The application platform is deployable; selected models and plugins are separate dependencies.
Langflow Self-Hosted
Visual builder and runtime for AI flows, agents and model integrations. Local model endpoints are configurable; a flow can also call externally hosted providers.
LibreChat Self-Hosted
Provides self-hosted multi-model chat, agents, file-backed retrieval and tool use over customer-selected model and data services.
MaxKB Community Edition
Self-hosted knowledge ingestion, document vectorization, RAG, question-answering and agent-workflow platform with configurable model providers.
Onyx Self-Hosted
Provides enterprise search, connectors and retrieval-augmented AI assistants over customer-selected knowledge sources.
Open WebUI Self-Hosted
Deployable team chat and model-access interface with retrieval features. It is an interface and application layer, not an included license or runtime for every connected model.
RAGFlow
Document understanding, knowledge ingestion and retrieval-augmented/agentic question answering with configurable LLM, embedding and reranking endpoints.

Review dates and sources appear on each listing. Functionality, edition, deployment and licensing must be checked together. Filter this category with cloud and deployment controls →

All categories · Suggest a listing or correction