Connects Confluence so wiki content can be searched and used as knowledge by the assistant.
Connects Dropbox as a file source so documents can be indexed and used as knowledge by the assistant.
Uses Google Gemini models as a supported AI provider for chat and the platform's planner/task graph.
Connects Jira so issues and project data can be reached from the assistant.
Connects Nextcloud as a file/document source for retrieval-augmented answers.
Runs local models through Ollama, including fully air-gapped deployments, as an alternative to hosted providers.
Uses OpenAI models as one of the supported AI providers for chat and task execution, selectable per task in the UI.
Connects ownCloud as a file/document source for retrieval-augmented answers.
Serves the same configured assistant to users over WhatsApp in addition to the web app, widget and email.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Build AI assistants on your own documents and put them wherever work happens: web, WhatsApp, email, Outlook, Nextcloud and ownCloud. Mix local models with the best cloud AI, see what every answer costs, and decide what the AI is allowed to do – open source, on your server or ours.
Run it in up to five minutes · Try it hosted · Docs · Discord
Self-hosting is free. The hosted version opens with a paid plan or an invitation code – ask us at team@synaplan.com.
Own your channels. One assistant answers on your website, in WhatsApp, by email, in Outlook and inside Nextcloud and ownCloud – with the same knowledge and the same rules everywhere.
Own your models. Hundreds of models from OpenAI, Anthropic, Google, Mistral, sovereign EU providers or locally via Ollama. Mix them per task: sensitive work stays local, everything else gets the best model for the job.
Own your costs. Every answer shows its model and price. A planner splits bigger requests into steps and spends the expensive model only where it matters.
Own the decisions. Actions like sending mail or creating tickets wait for your approval, and every step is logged.
Own the stack. On-prem, EU cloud or fully air-gapped. No training on your data, no forced telemetry, no feature paywall: self-hosted Synaplan is the same software as our cloud, under Apache-2.0.
Running in production at Megaherz Yoga · SANI Pflegedienst · National Secure Cloud · PlateArt
Related MCP server: laravel-simple-rag
You need: Docker with Compose v2 and 8 GB of RAM.
git clone https://github.com/metadist/synaplan.git
cd synaplan
make upOpen http://localhost:5173, log in as admin@synaplan.com / admin123 and say hello. Your first message starts the Synaplan Demo – no API key needed (40 messages a day for 14 days, how it works). When you're ready, add your own key (free: Groq) or run local models with Ollama.
The first start downloads everything and takes 5–15 minutes. After that, Synaplan starts in seconds.
These logins are for trying Synaplan on your own machine. On a server, use theinstaller – it creates its own admin password.
Where | How | Guide |
Your machine |
| |
Published image, no git | One | |
Docker GUI | Portainer, Dockge, Synology: paste the compose file as a stack | |
Closed network | No route to the internet, HTTPS on your LAN address | |
Linux server | The installer pins a release, generates secrets and runs a smoke test | |
Kubernetes | Helm charts for clusters | |
One click | – |
A Linux server in one line:
curl -fsSL https://raw.githubusercontent.com/metadist/synaplan/main/install.sh | \
bash -s -- --mode server --domain https://ai.example.comPublic sector & sovereign cloud (EU/CH): synaplan.eu covers openDesk, Nextcloud and OpenCloud deployments, on-premises or in an EU cloud.
People usually arrive comparing Synaplan with a chat window or an app builder. This is what each project is for. It is not a scoreboard.
Synaplan | Open WebUI | LibreChat | Dify | |
What it is | A team platform: chat, your files as knowledge, a site widget, and the same assistant on WhatsApp and email | A chat interface for local and cloud models | A chat app for many providers | A builder for AI apps and workflows |
First run | Several containers, about 4 GB | One container | A Compose stack | A Compose stack, and a hosted cloud |
Cost of an answer | Shown on the answer | Not on the answer | Not on the answer | In the builder's usage logs, not on the chat answer |
Same assistant on your site, WhatsApp and email | Yes | No | No | Site widget yes. WhatsApp and email are not built in |
If you only want a chat window, Open WebUI or LibreChat gets you there faster.
The same assistant, the same knowledge, the same model policy – on every channel your team and your customers already use.
Surface | What it does | Get it |
Web app | Full chat and admin UI, light and dark, five languages | This repo |
Mobile apps | Chat, documents and voice on iPhone and Android – on web.synaplan.com or your own server | |
Outlook add-in | Find and process mail inside Outlook (Web, new & classic, Mac) without sending it anywhere | |
Chat widget | Your assistant on any website with one snippet, human takeover included | |
WhatsApp & email | The AI answers on the channel the question came in on | |
Nextcloud, ownCloud & OpenCloud | Use your assistants inside your file cloud, with its files as knowledge – your file store stays in charge | |
Synaplan Desktop | Pair a computer and run skills on it (no installer yet – build from source) | |
MCP & Claude Code | Your knowledge and memories as MCP tools, plus an Anthropic-compatible endpoint |
Connects to Microsoft 365 · Dropbox · Nextcloud / ownCloud / WebDAV · CalDAV · IMAP · Jira & Confluence · your own MCP servers – how to connect
Stack: Symfony (PHP) backend, Vue frontend, MariaDB VECTOR or Qdrant for document search, Redis, Docker.
Lean core: app, database and Redis. Local AI, office files, web search, voice and more are building blocks you switch on when you need them.
Open by design: OpenAPI REST API, MCP server and client, an Anthropic-compatible /v1/messages endpoint and a plugin system – extend Synaplan without forking it.
Full feature list, every AI provider, all building blocks and developer commands: Platform reference.
Problem | What to do |
"Port already in use" on start | A port Synaplan needs is taken – see Port conflicts |
Containers stop right after start | Give Docker at least 8 GB of RAM, then check |
Chat gives no answers | Use the Synaplan Demo, paste one provider key, or add the |
First start seems stuck | The first start downloads all images and takes 5–15 minutes. |
Anything else | Ask in Discord or open a GitHub issue |
docs.synaplan.com – guides for users and admins
docs/README.md – the technical manual, in five learning tracks
Platform reference – install variants, features, providers and building blocks
Changing the code? Start with adding an AI provider or following a tool call.
We build Synaplan in the open. Tell us what you'd use it for, vote on ideas or show what you built in Discussions – we read everything.
💬 Discord – the fastest place for self-hosting and configuration questions
🐛 Issues – bugs and feature requests
🙌 Contributing – how to get your first pull request merged (AGENTS.md is the guide for coding agents)
🔒 Security policy – report a vulnerability privately
Apache-2.0 · Built in Düsseldorf by metadist · Member of the Open Source Business Alliance
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
One memory, every AI. A shared, user-owned markdown memory your AI clients read and write over MCP.
Persistent memory, knowledge graph, task management and more for AI agents via MCP.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
