One AI platform for every model, team, and workflow. Connect OpenAI, Claude, Gemini & Ollama — see every token and cost, stay GDPR compliant.
Try a quick AI chat on this page — no login
New releases, features, and fixes — straight from the repository.
No releases available
Link visitor questions to crawl targets or your own data. Drag questions onto sources to try mappings, or onto another question to reorder — the preview is for illustration only.
Widget flow
Drag a question or the dots at the ends of a line onto a source to connect. Drag onto another question to reorder. If a source is already used, mappings swap.
ProWith Pro you can connect CRM, ERP, or your own API for personalized answers next to crawled pages.
Visitor asks
Knowledge source
musterfirma.de/zeiten
musterfirma.de/pricing
API / CRM
docs/handbuch.pdf
docs/angebot.docx
Structured text
Example customer site
How the Synaplan widget appears on a visitor’s website — not the admin UI.
Synaplan AI
Online
Explore embedding, knowledge sources, industry examples, and how real teams deploy the widget.
Learn more about the chat widgetCapture preferences, tone, and facts as categorized memories. The neural view shows how they connect to your categories so the model can draft replies, automate email, and sound like you.
You open the web app — you describe tone and context in your own words. Each save adds a memory; the neural map grows category by category beside the conversation.
Memories
Physics preview — drag & collide
Legend
We are expanding guides for memory governance, inbox automation, and team workflows — start here and bookmark the hub.
Learn moreFrom model selection and cost control to logging and multilingual capabilities.
GPT, Claude, Gemini, Llama, and local Ollama models — routed automatically by cost, latency, and your own policies. No separate accounts, no copy-paste between tools.
Upload PDFs, Word files, or crawl entire websites. RAG retrieves the right context so the model answers from your data, not generic training.
Every prompt, response, model, and token count is logged with timestamps. Export for compliance or feed into your existing SIEM.
Embed a knowledge-grounded chatbot on any site via snippet or WordPress plugin. Multilingual, brand-customizable, GDPR-ready.
Track token usage, model costs, and response times in real time. Spot anomalies before they become budget surprises.
Self-host on your own infrastructure or use our EU cloud. Full data sovereignty, always.
See how organizations use Synaplan to deploy AI securely and efficiently.
“More time for mindfulness and less effort for organization.”
AI-powered support for course information and bookings.
“Caregivers need time for people.”
Automatic answers to frequent questions, reducing team workload.
“Authorities use Synaplan to securely process sensitive data.”
GDPR-compliant protective layer over external AI services.
“Straightforward AI use for support and internal processes.”
Secure AI integration without additional IT burden.
Synaplan is 100% open source. Inspect the code, contribute, or self-host — you're always in control.
Everything you need to know about Synaplan — from setup to GDPR compliance.
Synaplan is an open-source AI platform built on PHP 8.3+. It lets you connect multiple AI models (OpenAI, Anthropic, Groq, Gemini, Ollama), embed a chat widget on any website, search your documents with RAG (retrieval-augmented generation), and extend functionality with business-specific plugins — all in one self-hosted platform.
Yes. Unlike ChatGPT, Synaplan runs on your own infrastructure, supports multiple AI models simultaneously, is fully open source, and keeps all data within your control. You are not dependent on a single provider and can switch models at any time.
Absolutely. Synaplan can be self-hosted entirely within Germany or the EU — your data never leaves your servers. With local models via Ollama, no external API calls are made at all. This makes Synaplan one of the few AI platforms that can be operated in full GDPR compliance.
You embed a small JavaScript snippet into your website — just like a Google Analytics or live chat script. The widget connects to your Synaplan instance, uses your custom knowledge base (uploaded documents, FAQs, etc.), and can be styled to match your brand. Setup takes less than 10 minutes.
Synaplan supports OpenAI (GPT-5.5, GPT-5.5 Pro), Anthropic (Claude Opus 4.8), Google Gemini, Groq (ultra-fast inference), and Ollama for local self-hosted models. You can assign different models to different use cases or let the platform route automatically.
Yes — that is one of Synaplan's core strengths. A single `docker compose up -d` is all it takes. The standard setup (~9 GB) includes local AI via Ollama; the minimal setup (~5 GB) works with cloud APIs only (Groq, OpenAI). Runs on any standard Linux server.
Plugins are company-specific AI extensions that connect Synaplan to your existing business processes. Examples include SortX (AI-powered file management), marketing automation, and document workflows. You can use existing plugins or commission a custom plugin tailored to your company.
Synaplan is used by SMBs and enterprises across industries including hospitality, trades & crafts, healthcare, and technology. Website operators use the chat widget for customer service, while larger organizations use the full platform for internal knowledge management, document processing, WhatsApp integration, and email automation.
Start for free or chat with our AI directly via WhatsApp to get a clear AI roadmap for your organization.
Rather chat first? You can try the AI here without signing in.
