Local Chat
ChatGPT comfort without a word leaving the building
In practice →The rzfz.ai Stack
The rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — bundles curated open-source modules as Docker Compose containers, behind Caddy as the single externally reachable entry point and Authentik SSO, on the rzfz.ai Box, your own Ubuntu 26.04 servers, or in the cloud.
StackMap
The Stack Map
From the reverse proxy to the agents — the entire rzfz.ai Stack, live from the data, grouped by layer. Click, focus, or tap a tile for details.
- developed by razzfazz.ai GmbH
- Experimental
Agentic AI
Agent Manager
ExperimentalThe agent manager is an rzfz.ai-developed management interface where users launch, monitor and stop their own persistent agent instances — Hermes, Moltis, Coding Agents. It provisions per-user containers and volumes, registers their routes with Caddy, and reconciles them automatically after a reboot. Currently included as an experimental module.
MCP Manager
ExperimentalThe MCP manager is an rzfz.ai-developed management interface where users set up their own MCP integrations with their personal credentials — encrypted in an AES-256-GCM vault and isolated in a per-user proxy container. The MCP manager wires the integration automatically into that user's own Hermes, Moltis or coding agents. Currently included as an experimental module.
Hermes
ExperimentalBased on Hermes by Nous Research — packaged as a container for the stack by razzfazz.ai GmbH.
Hermes is a self-improving Python agent by Nous Research, which rzfz.ai packages as a container with persistent memory, more than 30 tools and an MCP client. In the stack, each user provisions their own Hermes instance through the agent manager, along with the Hermes Workspace UI for browsing memory and skills. Currently included as an experimental module.
Moltis
ExperimentalBased on Moltis — packaged as a container for the stack by razzfazz.ai GmbH.
Moltis is a personal agent server written in Rust with Matrix, Telegram and Discord gateways and sandboxed code execution, which rzfz.ai packages as a container. In the stack, each user provisions their own Moltis instance through the agent manager, with persistent memory. Currently included as an experimental module.
OpenHands
ExperimentalOpenHands is an autonomous coding agent that plans, writes, runs and tests code, spinning up per-task sandbox containers as it works. In the stack it integrates with Gitea for repositories and pull requests and with GPUStack for inference, and requires access to the Docker socket. Currently included as an experimental module.
Paperclip
ExperimentalBased on Paperclip — packaged as a container for the stack by razzfazz.ai GmbH.
Paperclip is an agent orchestrator that rzfz.ai runs as a container: it assigns roles and goals to teams of agents, distributes tasks and tracks budgets with an audit log. In the stack it integrates Gitea, Infisical and GPUStack, and is still in an early stage of development. Currently included as an experimental module.
Codex
ExperimentalCodex is an open-source terminal coding agent built by OpenAI. In the stack it runs as one of the sandboxed per-user containers in the persistent coding agents workspace, pre-wired against the local GPUStack model. Currently included as an experimental module.
Use cases that use this component
OpenCode
ExperimentalOpenCode is an open-source AI coding agent for the terminal. In the stack it runs as one of the sandboxed per-user containers in the persistent coding agents workspace, pre-wired against the local GPUStack model. Currently included as an experimental module.
Use cases that use this component
gsd-pi
Experimentalgsd-pi is an open-source tool for spec-driven development. It is no longer its own baked image, but an rzfz.ai-suggested user-defined install (`npm i -g @opengsd/gsd-pi`) inside the persistent coding agents workspace. Currently included as an experimental module.
Use cases that use this component
User Defined Coding Agents
ExperimentalAlongside Codex and OpenCode, the coding agents workspace also bundles a "user-defined" variant: its own rzfz.ai-developed container with a terminal and a protected sandbox, where users install any coding agent of their choice — such as Gemini CLI or Claude Code — and run it centrally around the clock, instead of a preconfigured tool. New in 2026.07-ga. Currently included as an experimental module.
Data & documents
Gotenberg converts HTML, Markdown and Office documents to PDF via Chromium and LibreOffice, behind a REST API. In the stack it serves as the conversion backend for Paperless-ngx and is also usable from Dify workflows; it runs internal-only.
Docling
ExperimentalDocling simplifies document processing: it parses diverse formats — including advanced PDF understanding — and integrates seamlessly with the generative-AI ecosystem. It supports input formats including PDF, DOCX, PPTX, XLSX, HTML and image formats, and exports to Markdown, HTML or JSON. For agentic AI, it ships plug-and-play integrations with LangChain, LlamaIndex, CrewAI and Haystack, and runs as an API or MCP server. Currently included as an experimental module.
Use cases that use this component
Presidio
ExperimentalPresidio is a PII-detection toolkit originally started by Microsoft and since transferred to the Data Privacy Stack organization: the Analyzer, Anonymizer and Image Redactor detect and redact more than 30 categories of personal data in text and images. In the stack it runs internal-only as a preprocessing step before documents are passed on to other modules. Currently included as an experimental module.
Use cases that use this component
Apache Tika
ExperimentalApache Tika extracts text, metadata and language from over a thousand file formats. In the stack it runs internal-only as the extraction backend for Paperless-ngx. Currently included as an experimental module.
Stirling PDF
ExperimentalStirling PDF is a powerful, open-source PDF editing platform that runs as a desktop app, in the browser, or on your own servers with a private API. It ships more than 50 PDF tools for editing, merging, splitting, signing, redacting, converting, OCR and compression, alongside enterprise features such as single sign-on and auditing. Currently included as an experimental module.
Crawl4AI
ExperimentalCrawl4AI is a web crawler built for LLMs that fetches page content via Chromium/Playwright and turns it into clean markdown or JSON. In the stack it distills web content for LightRAG, Cognee, Onyx and Dify to ingest — unlike SearXNG's plain URL discovery. Currently included as an experimental module.
Onyx
ExperimentalOnyx is an enterprise search platform with semantic search and LLM answers across more than 40 connectors, running its own Vespa index and embedding-model servers. In the stack it can connect Gitea and Paperless-ngx as data sources and, at six containers, is the heaviest module in the stack. Currently included as an experimental module.
Paperless-ngx
ExperimentalPaperless-ngx turns physical documents into a searchable online archive — so you can keep, well, less paper. It is the official successor to earlier Paperless versions and is developed in a community-driven way. Currently included as an experimental module.
Standard applications & security
Open WebUI is an extensible, feature-rich and user-friendly self-hosted AI platform that operates entirely offline. It supports LLM runners such as Ollama and OpenAI-compatible APIs and ships its own built-in RAG inference engine, plus granular access controls, real-time collaboration through channels, persistent memory, and voice and video capabilities — in the stack, rounded out by Speaches for voice input and output and SearXNG for web search.
Use cases that use this component
Dify is an open-source platform for building LLM applications that combines several capabilities in one interface: a visual workflow editor, a Prompt IDE, RAG pipelines for document ingestion, agent capabilities with more than 50 built-in tools, and LLMOps for monitoring production applications. It supports hundreds of proprietary and open-source LLMs; in the stack, the self-hosted community edition runs against the local GPUStack backend.
Use cases that use this component
SearXNG is a meta search engine that aggregates results from multiple search services without tracking or profiling users. In the stack, it powers web research — for example in Open WebUI and in Dify. SearXNG is open source and licensed under the AGPL-3.0.
Gitea is a self-hosted software development platform written in Go, built for an uncomplicated all-in-one development service. It bundles Git hosting, code review, issue tracking, a kanban board, a wiki, team collaboration, a package registry and CI/CD via Gitea Actions, which can reuse GitHub Actions workflows. Because it is written in Go, Gitea runs across many platforms and architectures, from Linux and macOS to Windows, FreeBSD and OpenBSD.
Use cases that use this component
Matrix
ExperimentalMatrix is an open network and an open standard for secure, decentralised and interoperable real-time communication. Synapse, the server implementation used in the stack, is developed and maintained by Element as an open-source Matrix homeserver. Currently included as an experimental module.
Vaultwarden
ExperimentalVaultwarden is an alternative server implementation of the Bitwarden Client API, written in Rust and compatible with the official Bitwarden clients, built for self-hosted deployments. It supports nearly all major Bitwarden features, including personal vaults, organizations, two-factor authentication and administrative tools. The project is community-maintained and not officially affiliated with Bitwarden, Inc. Currently included as an experimental module.
Infisical
ExperimentalInfisical is a developer-focused secrets management service with project/environment scoping, via CLI and REST API. In the stack, AI coding agents such as OpenHands use it to pull credentials at runtime, secured behind Authentik SSO. Currently included as an experimental module.
Operations
Based on docker-volume-backup by Offen — packaged as a container for the stack by razzfazz.ai GmbH.
The backup service is built into a container by rzfz.ai, but the underlying tool — docker-volume-backup — comes from Offen. It runs nightly, automated, GPG-encrypted backups of every database and volume in the stack, takes a database dump ahead of the volume snapshot, and retains backups for a configurable retention period.
The config portal is the rzfz.ai-developed central interface for configuring the stack: turning modules on and off, managing settings and secrets, uploading TLS certificates, triggering backups, and running a factory reset. It writes changes directly into the Docker Compose configuration and applies them.
The help center is an rzfz.ai-developed, locally hosted documentation hub for the stack. It renders the bundled guides and reference pages so support content stays available even without an internet connection.
The start portal is an rzfz.ai-developed landing page shown after login: it reads the enabled modules from the Compose configuration and links directly to every unlocked application.
Licenses is the rzfz.ai-developed license overview for the stack: it shows activation status and scope for every unlocked module and bundle.
Autoheal watches every container's Docker health checks and restarts unhealthy ones automatically. In the stack it's opted in specifically for the GPUStack family and the Presidio analyzer, whose worker processes occasionally wedge.
Komodo is a dashboard for container health, logs and restart controls. In the stack it monitors every Docker Compose stack, backed by its own database separate from the main system.
LLMs & RAG
GPUStack is an open-source GPU cluster manager for AI model serving and GPU instance provisioning. It orchestrates inference engines such as vLLM, SGLang and TensorRT-LLM across on-premises servers, Kubernetes and cloud environments, and covers a broad hardware ecosystem spanning NVIDIA and AMD GPUs to Ascend, Hygon and other accelerators. Its core capabilities include automated engine configuration, "day-0" support for newly released models, and monitoring and access controls. In the rzfz.ai stack, inference runs on a llama.cpp backend via Vulkan (GGUF models).
Use cases that use this component
- AI-assisted annual financial statement review & documentation
- Support email classification for IT operations
- Central RAG knowledge base for production control
- Local image analysis in patient care
- Framework for digitalization consulting
- Risk assessment of requirements
- Finding TARIC goods codes via RAG
Speaches is a speech-to-text and text-to-speech service that transcribes and synthesizes audio locally behind an OpenAI-compatible API. In the stack it powers voice input and output for Open WebUI and runs internal-only.
Cognee
ExperimentalCognee builds a knowledge graph from documents and data sources and answers questions via GraphRAG — more precise than plain vector search. In the stack it serves as the central company brain that chat, workflows and agents access through the MCP registry. Currently included as an experimental module.
Use cases that use this component
LightRAG
ExperimentalLightRAG is a dual-level GraphRAG framework that links entities and relationships for more precise retrieval answers. In the stack it uses GPUStack for embeddings and graph construction, serving as a lightweight alternative to Cognee for smaller knowledge bases. Currently included as an experimental module.
Use cases that use this component
Observability
ExperimentalObservability (OpenLIT + ClickHouse) measures cost, latency, token usage and prompts for every LLM call that flows through the chat pipeline. In the stack, access is restricted to a dedicated Authentik group, and a PII filter redacts prompt and completion text by default. Currently included as an experimental module.
Core
Caddy is the stack's reverse proxy and its single external entry point: all requests pass through ports 80/443, with TLS certificates managed automatically. A rate-limit plugin protects the login endpoints.
PostgreSQL with the pgvector extension is the stack's relational database — one instance with a separate database per module. It stores the data for Open WebUI, Dify, Authentik, GPUStack and other modules, and doubles as the vector store for RAG.
Authentik is the stack's identity provider: single sign-on, role-based access control and multi-factor authentication. It sits as a forward-auth gate behind Caddy in front of every module and decides, by group membership, who may reach which application.
Valkey is a Redis-compatible in-memory data structure store for caching and message queues. In the stack, several modules share one instance, each isolated on its own database index.
The SMTP relay is a Postfix mail server for outbound system messages. It runs internal-only and delivers notifications and password resets for modules like Authentik and Dify, either via an external provider or direct MX delivery.
The Docker socket proxy is a filtered access point to the Docker API. Modules that need to manage containers — such as the config portal, backup service, agent manager or Authentik — talk to Docker exclusively through this proxy, never through the unprotected host socket.
- developed by razzfazz.ai GmbH
- Experimental
Agent architecture — per user, sandboxed, all local
The Agent-Manager gives every user their own sandboxed agent — reachable from any local chat surface, with no cloud involved.
Local on your box · no cloud
Access — native, everywhere local
Open WebUI
Web terminal (OpenCode)
Matrix
Hermes · Moltis personal agents
Agent-Manager provisions · per user · sandboxed
Per user: sandboxed agent instances
Sandbox
Agent · User A
Sandbox
Agent · User B
Shared local services
Local LLM inference
RAG / knowledge Cognee · LightRAG
Documents Docling · Tika
Tools via MCP MCP-Manager → Gitea · web search
What the stack does for you
Seven core capabilities, ready to use on your own hardware — each already proven in real use cases.
Local Workflow Automation
Automate business processes with AI — on your own hardware
In practice →Local Knowledgegraph Brain
One central company brain for agents, chat and workflows
In practice →Local Personal Agents
Personal AI agents per employee — no Telegram, no WhatsApp needed
Local Coding Agents
No code leaves the box
In practice →Document OCR & Interpretation
From PDF to structured data — locally
In practice →PII Redaction
Detect and redact personal data — in text and images
In practice →Features
The rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — covers seven core scenarios end to end. Each feature combines several modules into a finished use case, entirely on your own hardware.
Local Chat
ChatGPT comfort without a word leaving the building
Open WebUI is the central chat interface for every model on the box — combining retrieval-augmented generation, web search and speech in/out in one interface. In the background, GPUStack with llama.cpp handles inference on your own GPU, so every request is answered locally. Because the model, vector search and interface all run on the same infrastructure, no prompt and no answer ever leaves the building — with no external API dependency at all. In practice, Open WebUI serves as the front end for central knowledge bases and industry-specific RAG applications, from production control to foreign trade.
Modules: Open WebUI, GPUStack + llama.cpp
In practice: Central RAG knowledge base for production control , Finding TARIC goods codes via RAG
Local Workflow Automation
Automate business processes with AI — on your own hardware
Dify orchestrates business processes as visual workflows — from simple classification to multi-step document pipelines with approval steps. Every node in the workflow runs against the stack's local models, so automations can be assembled without programming knowledge and tested directly against real business data. Because orchestration and inference run on the same box, sensitive client and customer data stays in house throughout processing. In production, Dify already classifies support emails for an IT service provider, supports accounting processes at a tax advisory firm, and structures digitalization projects in consulting.
Modules: Dify
In practice: Support email classification for IT operations , AI-assisted annual financial statement review & documentation , Framework for digitalization consulting
Local Knowledgegraph Brain
One central company brain for agents, chat and workflows
Cognee builds a knowledge graph across your documents and systems and answers questions via GraphRAG instead of plain keyword search — more precise for complex relationships and across document boundaries. In the stack it serves as shared memory that chat, workflows and agents access through the MCP registry, instead of every module keeping its own knowledge. Because the knowledge graph is built entirely on your own hardware, internal documents and process knowledge stay in house — Cognee is currently included as an experimental module and under active development. At one production company it already consolidates manuals, incident history and process documentation into one central knowledge base that staff query simply via chat.
Modules: Cognee
In practice: Central RAG knowledge base for production control
Local Personal Agents
Personal AI agents per employee — no Telegram, no WhatsApp needed
Every employee provisions their own personal agents through the agent manager — Hermes as a Python agent with persistent memory and more than 30 tools, Moltis as a Rust-based agent server with Matrix integration. They are reached the normal way, through Open WebUI, with no need for Telegram, WhatsApp or any other external messenger. Because the agent manager, Hermes and Moltis all run on the same box as the models, memory contents and conversations stay entirely local — all three are currently included as experimental building blocks of the stack. This makes it possible to build personal assistants that remember earlier requests and take on tasks independently, without data ever leaving your own infrastructure.
Modules: Agent Manager, Hermes, Moltis
Local Coding Agents
No code leaves the box
Coding agents run in a protected container terminal on the box or master — with access to the local Gitea and on-box coding models. They take on bounded jobs like raising test coverage, refactorings or spec-driven implementation and deliver results as merge requests. With models, code and git server on the same infrastructure, there are no external API keys and not a single line of code leaves the premises. One customer already runs an agent that raises unit-test coverage around the clock.
Modules: Codex, OpenCode, gsd-pi, Gitea, OpenHands
In practice: 24×7 dev agent raising test coverage , Local coding with on-box models
Document OCR & Interpretation
From PDF to structured data — locally
Docling, Tika and Gotenberg read, convert and interpret documents of every kind — from PDFs and Office files to scanned receipts with layout analysis. Vision models on your own GPU handle image recognition, while Stirling PDF is available as a toolbox for merging, splitting and converting. Because the entire pipeline — recognition, conversion and vision inference — runs on the same infrastructure, invoices, contracts and other sensitive documents never leave the building; Docling, Tika and Stirling PDF are currently included as experimental modules. In production, this pipeline already pre-processes receipts for a tax advisory firm and extracts inbound customer documents before sensitive data gets redacted.
Modules: Docling, Apache Tika, Gotenberg, Stirling PDF
In practice: AI-assisted annual financial statement review & documentation , Document extraction and redaction of sensitive data
PII Redaction
Detect and redact personal data — in text and images
Microsoft Presidio detects and anonymizes personal data in document pipelines before it is passed on to other modules — more than 30 categories, in text as well as in images. The Analyzer identifies sensitive spots, the Anonymizer redacts or replaces them, and the Image Redactor does the same job for photos and scans. Presidio runs internal-only as a preprocessing step on the same box as the other modules — personal data gets redacted before it ever reaches a language model; the module is currently included as an experimental building block of the stack. It is already used to redact inbound customer documents and, in image analysis for patient care, to keep sensitive health data entirely within the facility.
Modules: Presidio
In practice: Document extraction and redaction of sensitive data , Local image analysis in patient care
The stack in action
Management UI
Manage it all in one place
The rzfz.ai-developed management UI runs the whole stack — backup & restore, updates, secrets, users. No shell required.
Agents
Personal & coding agents
The agent manager gives every user their own persistent agents. Coding agents run in a sandbox inside the stack — source code never leaves the box.
Local LLM
Models run locally — GPUStack
GPUStack serves the language models on your own hardware — no request ever calls out to a cloud.
Privacy
Personal data stays redacted
Presidio finds and redacts personal data before a document goes anywhere else — automated, local and auditable.
Knowledge Graph
Your organization's memory
Cognee turns your documents into a living knowledge graph — entities, relationships and summaries your agents reason over like a shared memory. All local, on your box.
Developed by rzfz.ai
The stack is more than the sum of its open-source parts: we build these components ourselves — the first-party layer that turns loose OSS into a product.
Config UI
The Management UI: run the whole box from one screen
The rzfz.ai-developed management UI is the stack's control center — not just a backup tool, but a full operations cockpit: turn modules on and off, manage secrets, roll out updates, trigger backups, upload certificates, and run a factory reset when things go wrong.
One dashboard, many views — modules, module configuration, Help Center and licenses below.
Start portal
Start portal: one click to every module
After login, users land on the rzfz.ai-developed start portal — a landing page that automatically links every unlocked module. No bookmark chaos, no hunting for the right URL.
Agent manager
Agent manager: run personal and coding agents
The agent manager gives every user their own persistent agents — including coding agents that run in a sandbox inside the stack. The MCP manager wires matching integrations into those agents automatically.
Custom coding agent
Bring your own coding-agent tool
Prefer your own coding-agent tool? Install it as a user-defined coding agent in the persistent workspace — configured directly through the agent manager.
All seven building blocks at a glance
Config Portal
Config portal — central interface for configuring the rzfz.ai stack
Help Center
Help center — locally hosted documentation and support articles for the stack
Start Portal
Start portal — landing page linking to every unlocked module in the stack
Licenses
License management — activation and status of unlocked modules and bundles
Agent Manager
Agent manager — management and monitoring of every agent running in the stack
MCP Manager
MCP manager — registration and permissioning of MCP servers for agents
User Defined Coding Agents
User-defined coding agents — free choice of your own coding-agent tool in a persistent workspace
"Nothing leaves the box unless a module is explicitly configured to reach out."
Hardening & compliance
The rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — is hardened for enterprise use: identity, network and compliance are designed in from the start, not bolted on afterward.
Identity & access
Authentik sits in front of every module — no service is reachable without signing in. Role-based access control (RBAC) and multi-factor authentication (MFA) are the default, not an add-on.
Network hardening
- Caddy is the only externally reachable entry point — with rate limiting against abuse.
- The Docker daemon is never directly exposed; a Docker socket proxy mediates every access.
- An SSRF proxy filters outbound HTTP calls from workflows before they leave the network.
- Every service port is bound to localhost — nothing listens on a public interface.
Compliance
The security documentation includes mapping tables for NIS2 and ISO 27001, plus an assessment against the OWASP LLM Top 10. Every release ships with an SBOM and a security assessment.
Secrets & backups
Secret rotation tooling and GPG-encrypted backups are part of standard operations — no plaintext credentials, no unencrypted backups.
Commercial operation
The community edition, the rzfz.ai subscription and the separately bookable services are described in full on the Enterprise page — including prices and what is explicitly not included.
Releases
The rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — is versioned with CalVer and currently ships on a monthly release cycle. The list below shows every release, newest first.
Roadmap
2026.09 and beyond
Directional — planned features, subject to change.
Coming in 2026.09
- LLM Manager — one console for the whole inference fleet: worker management, model deployment straight from the HuggingFace catalogue, live dashboards, a playground plus per-API-key usage and cost overview.
- Managed worker nodes — attach additional inference nodes with a single command; runner images are distributed, updated and rolled back centrally by the master.
- Unified agent portal — all personal agents (coding tools, Hermes, Moltis) in one interface with a multi-pane view.
- Stack-wide LLM observability — chat, workflows and agents feed cost, latency and token metrics into one shared dashboard.
- Platform currency — Open WebUI 0.11, Dify 1.16.1 and a base-image refresh across the whole stack.
On the horizon
- Log and metric export into customer-owned SIEM and monitoring systems.
- Support for new model architectures and faster inference through speculative decoding.
- GRC building blocks for security monitoring and ISMS support (under evaluation).
-
v2026.08-ga
Offline & air-gapped operation: the box runs, installs and updates entirely without internet.
- Offline & air-gapped — installation, updates and module operation without internet access: offline bundles including every image, completeness checks before each restart, optional kernel-side egress sealing of the host.
- Apple Silicon inference — Mac machines serve as local inference nodes, integrated seamlessly into the box through a gateway.
- rzfz.ai ShortCuts — curated mini-apps for business users, managed through the start portal.
- Enterprise documentation portal — access-protected customer documentation at docs.rzfz.ai.
- Domain change in one click — a changed box domain name now propagates fully: SSO provider, login URLs and every service follow automatically.
- Password manager hardened — Vaultwarden stores in PostgreSQL (part of the standard backup), SSO login issues fixed, compatibility with current Bitwarden clients.
- Security and currency sweep — including a critical Gitea hotfix (CVE-2026-59774), updates for Matrix, LightRAG, Valkey and base images; four hardened internal auth paths.
- Continuously hardened across 15 patch releases; public downloads now on GitHub (github.com/rzfz-ai/rzfz-ai-service-stack).
-
v2026.07-ga
Open-core licensing goes public: Apache-2.0 Community, the rzfz.ai Subscription and coding-agent workspaces
- Open-core licensing, delivered publicly — a free Apache-2.0 Community tier, a source-available tier (BUSL-1.1) under the rzfz.ai Subscription, a live license overview, a public GitHub mirror and a published Community Wiki
- Coding-agent workspaces — personal coding agents are now per-type sandboxed containers (OpenCode, Codex, user-defined) with live web-app preview plus per-user MCP integrations and memory
- Dify 1.15.0 — single sign-on no longer asks you to log in twice
-
v2026.06-ga
One default model: qwen3.6 at 1M context for chat, coding and vision
- qwen3.6 is the one default model for chat, coding, general tasks and vision at 1M context — no per-role model juggling
- Document Q&A works out of the box — the reranker and chunking defaults that make RAG find the right facts ship pre-configured
- Smoother upgrades — both the standard and the from-2026.04 upgrade paths are validated, with upgrade self-healing and journaling
- Unattended USB appliance — a bootable USB image performs an unattended Ubuntu 26.04 install and prepares the stack for first boot
- Audit-ready compliance tables — structured NIS2 (EU 2022/2555) and ISO/IEC 27001:2022 evidence in the security architecture
-
v2026.05-ga
Per-user personal agents: Hermes, Moltis and coding agents in the "My Agents" drawer
- rzfz.ai start portal — tile launcher with per-user pinning
- New Crawl4AI module and observability profile (OpenLIT + ClickHouse)
- Open WebUI ↔ Dify manifold pipe
-
v2026.04-GA
One command from base install to fully configured stack: razzfazz-post-install.sh
- razzfazz-post-install.sh automates GPUStack model deployment plus Open WebUI and Dify setup in one step
- Two experimental RAG modules: LightRAG (graph-aware) and Cognee with FalkorDB
- Encrypted .env snapshots before every configuration change; AMD GPU inference fix
System requirements
The rzfz.ai Stack — the integrated open-source stack for local AI infrastructure — supports only Ubuntu 26.04 LTS as an operating system. The same rule applies to every deployment profile: We name the limits before you find them.
rzfz.ai Box
AMD Strix Halo (Ryzen AI MAX+), 128 GB unified memory
32 GB container budget + 96 GB VRAM (raisable to 110 GB)
Requirements
- Ubuntu 26.04 LTS (pre-installed)
- Network access, ports 22/80/443
Limitations
- AMD-only inference — no NVIDIA/CUDA path on the box
- vLLM currently unsupported on Strix Halo (production: llama.cpp via Vulkan)
- The 32 GB container budget limits how many modules run concurrently
- One intensive agent loop at a time — sizing rule ~1 box per 6–10 employees
Own server / VM without GPU
Any Ubuntu 26.04 host, ~16–24 GB RAM
Requirements
- Ubuntu 26.04 LTS, kernel 7.x
- Docker Engine + Compose v2
Limitations
- CPU inference is slow — fine for light or batch workloads, not for interactive agents
- As a control plane it delegates inference to GPU workers (boxes or cloud)
NVIDIA/CUDA server
Ubuntu 26.04 host with NVIDIA GPUs — own hardware or GPU cloud
Requirements
- Ubuntu 26.04 LTS
- CUDA-capable NVIDIA GPU(s)
- Docker Engine + Compose v2
Limitations
- Inference via llama.cpp on CUDA, models in GGUF format
- The VRAM ceiling is a budget question, not an architectural one
Cloud instance
Any Ubuntu 26.04 cloud instance — with GPU as worker, without GPU as control plane
Requirements
- Ubuntu 26.04 LTS
- Docker Engine + Compose v2
Limitations
- Data sovereignty depends on the cloud provider — for strictly local scenarios choose the box or own hardware
Mixed fleets
Many teams combine profiles instead of committing to one: a control plane without its own GPU orchestrates several rzfz.ai boxes as local inference workers and, when needed, pulls in additional cloud GPU workers for peak load. Core operations stay local — peak load is covered by resources booked from the cloud, without giving up data sovereignty. Find matching combinations under Bundles.
What do you need? What system do you have?
Type a need or your system — we tell you honestly how it fits the stack.
How integration works with us
Prewired
A module in the stack already covers it — ready to use, no extra work.
Dify plugin
The Dify Marketplace covers it — the stack inherits it automatically. for technicians
REST / MCP
If your system speaks REST or MCP, it connects directly — no detour.
Custom · built by us
Local, niche business software that's in no catalog — that's exactly what we build the integration for.
-
Chat / assistant
PrewiredPrewired — Open WebUI gives you ChatGPT-grade chat, fully local.
Matching use cases: Central RAG knowledge base for production control , Finding TARIC goods codes via RAG
-
Knowledge base / RAG
PrewiredPrewired — cognee/LightRAG build a local company brain over your documents.
Matching use cases: Central RAG knowledge base for production control , Finding TARIC goods codes via RAG
-
Document analysis / OCR
PrewiredPrewired — Docling reads and structures PDFs & scans, incl. OCR.
Matching use cases: AI-assisted annual financial statement review & documentation , Document extraction and redaction of sensitive data
-
PII redaction
PrewiredPrewired — Presidio detects and redacts personal data automatically.
Matching use cases: Document extraction and redaction of sensitive data , Local image analysis in patient care
-
Workflow automation
PrewiredPrewired — Dify orchestrates your AI workflows locally.
Matching use cases: Support email classification for IT operations , AI-assisted annual financial statement review & documentation , Framework for digitalization consulting
-
Speech recognition
PrewiredPrewired — local speech-to-text, no cloud.
-
Email
REST / MCPConnected via REST/MCP or a Dify plugin — IMAP/SMTP/Graph speak standard protocols.
Matching use cases: Support email classification for IT operations
-
MS Office / SharePoint
REST / MCPConnected via the Microsoft Graph API (REST) or a Dify plugin.
-
Google Workspace
REST / MCPConnected via the Google Workspace REST APIs or a Dify plugin.
-
SAP
REST / MCPSAP speaks REST/OData — directly connectable; complex scenarios we build as a custom integration.
-
BMD (accounting)
Custom · built by usLocal business software like BMD isn't in any catalog — we integrate it for you.
Matching use cases: AI-assisted annual financial statement review & documentation
-
Sage DPW (HR)
Custom · built by usHR systems like Sage DPW we connect as a custom integration — even without an off-the-shelf connector.
-
ERP / inventory
REST / MCPIf your ERP speaks REST/MCP it connects directly; otherwise we build the bridge.
-
Local / niche software
Custom · built by usThe local, niche software no catalog lists — that's exactly our strength: we integrate it.
-
Any system with an API
REST / MCPAnything that speaks REST or MCP integrates immediately.
-
Dify marketplace tool
Dify pluginEverything in the Dify Marketplace the stack inherits automatically — for technicians.
No match — but if it speaks REST or MCP, we can connect it. Ask us.