Synaplan
Officialby metadist
README.md
<div align="center">
<a href="https://www.synaplan.com"><img src="docs/images/hero.svg" alt="Synaplan — We produce AI freedom" width="100%"></a>
**We produce AI freedom.**
Open-source, self-hosted AI platform (PHP/Symfony): chat with any model, RAG over your docs, embeddable widget, MCP — see the cost of every answer. Apache-2.0.
[Website](https://www.synaplan.com) · [Docs](https://docs.synaplan.com/) · [Live instance](https://web.synaplan.com/) · [iOS](https://apps.apple.com/app/id6784278288?ct=github-readme) · [Android](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme) · [Desktop](https://github.com/metadist/synaplan-desktop) · [Outlook Add-in](https://github.com/metadist/Synamail) · [Discord](https://discord.com/invite/kQB3eDjWfF)
[](LICENSE)
[](https://github.com/metadist/synaplan/stargazers)
[](#quickstart)
[](https://apps.apple.com/app/id6784278288?ct=github-readme)
[](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme)
[](https://discord.com/invite/kQB3eDjWfF)
[](https://web.synaplan.com/api/doc)
</div>
---
<p align="center">If Synaplan is useful to you, a star helps the next person find it.</p>
<p align="center">
<img src="docs/images/synaplan-admin-tour.gif" alt="A thirty-second tour of Synaplan: a chat answer and its cost, default models with cost badges, the file library, generated images and audio, and connected apps" width="100%">
</p>
<p align="center"><sub>Chat, what each answer cost, your files, generated media, and the apps you can connect. About 30 seconds.</sub></p>
## Quickstart
```bash
git clone https://github.com/metadist/synaplan.git
cd synaplan
make up
```
Open **<http://localhost:5173>**. Log in as `admin@synaplan.com` / `admin123` and paste one provider key. Free: [Groq](https://console.groq.com).
A published image, a Docker GUI, a closed network, or a Linux server: [More ways to install](#more-ways-to-install).
## How it compares
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.
---
## Why Synaplan
- **Freedom, not a plan tier.** The whole platform — backend, frontend, widgets, plugins — is Apache-2.0 and starts with one command. Self-hosted is the same software as the cloud.
- **Hundreds of models, one place.** OpenAI, Anthropic, Google Gemini, Groq, Mistral, xAI, HuggingFace, sovereign EU providers, and any local model via Ollama. Swap a provider per task in the UI.
- **The planner spends the expensive model only where it matters.** A request becomes a small task graph (extract → summarize → generate → reply). Live cards show the steps. Every answer shows what it cost.
- **Yours, including offline.** On-prem, EU cloud, or fully air-gapped. No training on your data. No forced telemetry.
- **Where you already work.** Web, [iPhone](https://apps.apple.com/app/id6784278288?ct=github-readme), [Android](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme), [Desktop](https://github.com/metadist/synaplan-desktop), [Outlook](https://github.com/metadist/Synamail), a chat widget, WhatsApp, email — plus Microsoft 365, Dropbox, Nextcloud / ownCloud, calendars, Jira, Confluence and [OpenCloud](https://github.com/metadist/synaplan-opencloud).
- **Extend it without a fork.** Plugins, an OpenAPI REST API, an MCP server and client, and an Anthropic-compatible endpoint for Claude Code and friends. Optional sidecars stay off until you turn them on.
---
## Take the tour
<p align="center"><a href="https://www.youtube.com/watch?v=WjO9mE43uec">▶ Watch the full demo on YouTube</a></p>
Click any screenshot to see it full size.
<table>
<tr>
<td width="25%" align="center">
<a href="docs/images/tour/chat.webp"><img src="docs/images/tour/thumbs/chat.webp" alt="Chat with per-model cost tracking" width="100%"></a><br>
<sub><b>Chat</b><br>Every answer shows what it cost</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/provider-setup.webp"><img src="docs/images/tour/thumbs/provider-setup.webp" alt="AI provider setup with live key validation" width="100%"></a><br>
<sub><b>Provider setup</b><br>One key, tested and encrypted</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/model-selection.webp"><img src="docs/images/tour/thumbs/model-selection.webp" alt="Per-task model selection with cost badges" width="100%"></a><br>
<sub><b>Model choice</b><br>A different model per task</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/rag-search.webp"><img src="docs/images/tour/thumbs/rag-search.webp" alt="Semantic search across uploaded documents" width="100%"></a><br>
<sub><b>RAG search</b><br>Semantic search over your files</sub>
</td>
</tr>
<tr>
<td width="25%" align="center">
<a href="docs/images/tour/media-generation.webp"><img src="docs/images/tour/thumbs/media-generation.webp" alt="Gallery of AI-generated images and video" width="100%"></a><br>
<sub><b>Media generation</b><br>Images, video and audio in chat</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/chat-widget.webp"><img src="docs/images/tour/thumbs/chat-widget.webp" alt="Embed code for the chat widget" width="100%"></a><br>
<sub><b>Chat widget</b><br>One snippet, any website</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/system-prompts.webp"><img src="docs/images/tour/thumbs/system-prompts.webp" alt="System prompt editor" width="100%"></a><br>
<sub><b>AI instructions</b><br>Your own system prompts</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/file-manager.webp"><img src="docs/images/tour/thumbs/file-manager.webp" alt="File manager with folders and storage quota" width="100%"></a><br>
<sub><b>Files</b><br>Uploads become knowledge</sub>
</td>
</tr>
<tr>
<td width="25%" align="center">
<a href="docs/images/tour/plugins.webp"><img src="docs/images/tour/thumbs/plugins.webp" alt="Plugin view showing Synaform collections" width="100%"></a><br>
<sub><b>Plugins</b><br>Extend without forking</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/admin-panel.webp"><img src="docs/images/tour/thumbs/admin-panel.webp" alt="Admin panel with system info and user counts" width="100%"></a><br>
<sub><b>Admin</b><br>Users, usage and health</sub>
</td>
<td width="25%" align="center">
<a href="docs/images/tour/branding.webp"><img src="docs/images/tour/thumbs/branding.webp" alt="White-label branding settings" width="100%"></a><br>
<sub><b>Branding</b><br>White-label the whole app</sub>
</td>
<td width="25%"></td>
</tr>
</table>
<sub>Regenerate these assets after a UI change with <code>scripts/build-readme-tour.sh</code>.</sub>
---
## More ways to install
The [quickstart](#quickstart) is a local checkout. The variants below are a published image, a machine with no route to the public internet, and a Linux server.
### On this machine
The [quickstart](#quickstart) is this path. Open **<http://localhost:5173>**. A status screen is up within seconds and lists every boot step, then switches to the app when it is ready. First start: 5–15 minutes. Later starts: seconds.
`make up` answers on `:5173` before the rest of the images finish pulling. `docker compose up -d` starts the same stack; `:5173` stays quiet until those pulls finish.
1. Log in as `admin@synaplan.com` / `admin123`. The status screen shows this too.
2. Paste one provider key. Free: [Groq](https://console.groq.com). The app opens **AI provider setup** until a key is in place. You do not edit a config file for that.
3. Same notes in the terminal: `docker compose logs -f startup-notes`.
No cloud key? `COMPOSE_PROFILES=local-ai ENABLE_LOCAL_GPT_OSS=true make up` pulls a local chat model (`gpt-oss:20b`, ~14 GB). Chat starts when the download finishes.
### Published image, no git checkout
One file is enough. A `.env` beside it is optional.
```bash
mkdir synaplan && cd synaplan
curl -fsSL -o compose.yaml https://raw.githubusercontent.com/metadist/synaplan/main/deploy/quickstart/compose.yaml
docker compose up -d
```
Open **<http://127.0.0.1:8000>**. The first visit opens the setup: create the administrator, paste one provider key (free: [Groq](https://console.groq.com)), done. The first start pulls the images and takes a few minutes.
**Docker GUI** (Portainer, Dockge, Synology Container Manager, …): create a stack, paste [`deploy/quickstart/compose.yaml`](deploy/quickstart/compose.yaml) as its compose file, deploy. Any setting from [`deploy/quickstart/.env.example`](deploy/quickstart/.env.example) goes into the stack's environment variables — nothing is required. When the GUI runs on another machine (a NAS or a server), add `SYNAPLAN_HTTP_BIND=0.0.0.0` and `SYNAPLAN_URL=http://<that machine's IP>:8000`; without them Synaplan only opens on that machine itself. Dockge marks the stack "exited" once the one-time `secrets-init` step has finished; that is expected, and Synaplan keeps running.
**Settings** go into `.env`, then `docker compose up -d` again (in a GUI: the stack's variables, then redeploy):
- `SYNAPLAN_VERSION` picks a release tag from the [releases page](https://github.com/metadist/synaplan/releases). Empty means the release this file was published with. Never `latest`.
- `SYNAPLAN_HTTP_BIND=0.0.0.0` plus `SYNAPLAN_URL=http://<this machine's IP>:8000` opens it to your network. `SYNAPLAN_URL` must be the address people type, or live chat stays disconnected. Over plain `http://` on a network address, browsers block the microphone and copying to the clipboard; chat and files work. For those two, use [Closed network](#closed-network) HTTPS.
- Provider keys, a bootstrap administrator and mail are listed in the example with one line each.
**Data** lives in named Docker volumes — the database, uploads, vectors and the generated secrets. Keep them together: a database without its `secrets` volume does not start. `docker compose down` keeps everything; `docker compose down -v` deletes it all.
**Change the release:** back up the volumes, set `SYNAPLAN_VERSION`, run `docker compose up -d` (or redeploy the stack in the GUI). Going back to an older tag after a newer one migrated the database means restoring that backup. The steps are in [Update a self-hosted deployment](docs/UPDATE_SELFHOST.md#quickstart-volumes).
Office documents, local AI, file work, closed-network TLS and scripted backups use the full [`deploy/compose.yaml`](deploy/compose.yaml) with [`deploy/selfhost.env.example`](deploy/selfhost.env.example) instead.
### Closed network
Opt-in. The default stays `http://127.0.0.1:8000` on this machine.
Turn it on when the network has **no route to the public internet** and people open Synaplan by the machine's address. Chat needs `https://<address>/`. The machine creates the certificate. The browser warns once.
Any IPv4 address on that network works, including `10.0.0.0/8`, `172.16.0.0/12`, `192.168.0.0/16`, `100.64.0.0/10` and `169.254.0.0/16`, plus a block you assigned and do not announce.
```bash
cp deploy/selfhost.env.example deploy/.env
# Set SYNAPLAN_VERSION. Leave SYNAPLAN_HTTP_BIND at 127.0.0.1.
deploy/scripts/local-tls.sh 10.0.0.15
deploy/scripts/prepare.sh
docker compose --env-file deploy/.env -f deploy/compose.yaml pull
deploy/scripts/validate-release.sh
docker compose --env-file deploy/.env -f deploy/compose.yaml up -d
```
Colleagues open **https://10.0.0.15/**. Ports 80 and 443 must be free. The app itself stays on `127.0.0.1:8000`. A second interface is another argument: `deploy/scripts/local-tls.sh 10.0.0.15 192.168.1.20`. A public name keeps your own HTTPS proxy and leaves this off.
Details: [docs.synaplan.com/local-network](https://docs.synaplan.com/local-network) · [deploy/README.md](deploy/README.md#local-network).
### On a server
The commands above are the development stack (source build, Vite, MailHog, phpMyAdmin) or the published image. For a Linux server, the installer writes `deploy/.env`, pins the latest release, and runs prepare → pull → validate → start → smoke-test. Secrets land in `deploy/data/secrets.env`.
```bash
curl -fsSL https://raw.githubusercontent.com/metadist/synaplan/main/install.sh | \
bash -s -- --mode server --domain https://ai.example.com
```
The same steps by hand are in [Installation](docs/INSTALLATION.md) and [deploy/README.md](deploy/README.md). Flags: `bash install.sh --help`.
One-liner for the development stack, if you would rather not clone by hand:
```bash
curl -fsSL https://raw.githubusercontent.com/metadist/synaplan/main/install.sh | bash
```
---
## One AI, everywhere you work
The same assistant, the same knowledge base, the same model policy — on every channel your team already uses. Connect a system once under **Channels**; the planner can then read from it and deliver results into it.
### Conversation surfaces
| Surface | What it does | Get it |
|---------|--------------|--------|
| **Web app** | Full chat + admin UI, light/dark, five languages | This repo — `make up` |
| **Mobile apps** | Chat, documents and voice on iPhone and Android — pointed at web.synaplan.com or your own server | [App Store](https://apps.apple.com/app/id6784278288?ct=github-readme) · [Google Play](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme) |
| **Synaplan Desktop** | Pair a computer and run skills on it. In the web app: **Channels → Synaplan Desktop**. No installer yet — build from the repository. | [metadist/synaplan-desktop](https://github.com/metadist/synaplan-desktop) |
| **Outlook add-in** | Bring Synaplan into Outlook (Web, new & classic, Mac) — find and process mail without sending it anywhere | [metadist/Synamail](https://github.com/metadist/Synamail) |
| **Chat widget** | Embed your assistant on any website with one snippet — cross-origin ready, human takeover included | [Widget guide](https://docs.synaplan.com/index.php/widget) |
| **WhatsApp & Email** | The AI answers on the channel the question came in on | [WhatsApp](docs/WHATSAPP.md) · [Email](docs/EMAIL.md) |
| **MCP & Claude Code** | Your RAG and memories as MCP tools; Anthropic-compatible `POST /v1/messages` endpoint | [MCP guide](https://docs.synaplan.com/index.php/mcp) · [guide](docs/ANTHROPIC_COMPATIBLE_API.md) |
### Connected systems
Set these up under **Manage → Connections** (or **Manage → Connections → MCP Servers** / **Manage → Channels → Email**). In chat, use the channel word shown as a pill on the Connections page — for example *nextcloud*, *dropbox*, *outlook*.
| Channel | What it unlocks | Setup |
|---------|-----------------|-------|
| **Microsoft 365** | Live Outlook mail search, calendar events (`outlook`), send from your own mailbox | **Manage → Connections** — OAuth, no password stored |
| **Dropbox** | Save generated files into a Dropbox folder (`dropbox`) | **Manage → Connections** — OAuth |
| **Nextcloud / ownCloud / WebDAV** | File results into a folder you own (`nextcloud` / `folder`) | **Manage → Connections** — app password, never your account password |
| **CalDAV calendar** | Put generated meetings into a calendar you own (`calendar`) | Same Nextcloud preset can create folder + calendar in one step |
| **IMAP mailbox** | Live search of any IMAP inbox, merged with Microsoft 365 results | **Manage → Channels → Email** |
| **Jira & Confluence** | Search and summarize; create tickets or pages when you allow writes. A pasted Confluence page is read through the signed-in account | **Manage → Connections → MCP Servers** — Jira & Confluence card, then sign in with Atlassian (no API token) |
| **Saved Tasks** | Pin a plan and run it on demand or on a schedule (hourly / daily / weekdays) | **Manage → Automations → Saved Tasks** |
| **Nextcloud / OpenCloud apps** | Use files from those clouds as AI knowledge — the file store stays in charge | [synaplan-nextcloud](https://github.com/metadist/synaplan-nextcloud) · [synaplan-opencloud](https://github.com/metadist/synaplan-opencloud) |
Details and channel words: [docs/CONNECTIONS.md](docs/CONNECTIONS.md).
---
## The Synaplan ecosystem
Everything below is the same platform, packaged for different homes. Pick what fits — nothing else is required.
| Project | What it is |
|---------|------------|
| **[synaplan](https://github.com/metadist/synaplan)** | The platform itself (this repo): backend, frontend, widget, plugins, dev stack, and the `deploy/` production contract with Elestio, AWS Marketplace, and Umbrel adapters |
| **[synaplan-charts](https://github.com/metadist/synaplan-charts)** | Helm charts for Kubernetes — for partners and enterprises running K8s clusters |
| **[Mobile apps](https://github.com/metadist/synaplan-apps)** | Native iOS and Android — [App Store](https://apps.apple.com/app/id6784278288?ct=github-readme) · [Google Play](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme) |
| **[synaplan-desktop](https://github.com/metadist/synaplan-desktop)** | Synaplan Desktop — pair a computer and run skills on it. No installer yet; build from source. |
| **[Synamail](https://github.com/metadist/Synamail)** | Outlook add-in (Web, new & classic, Mac) — Synaplan inside your mailbox |
| **[synaplan-nextcloud](https://github.com/metadist/synaplan-nextcloud)** / **[synaplan-opencloud](https://github.com/metadist/synaplan-opencloud)** | Apps for Nextcloud / OpenCloud — use those files as AI knowledge while the file store stays in charge (ownCloud works via the built-in WebDAV connection) |
| **[synaplan-tts](https://github.com/metadist/synaplan-tts)** | Optional self-hosted text-to-speech service for voice output |
| **[synaplan-base-php](https://github.com/metadist/synaplan-base-php)** | The base Docker image (FrankenPHP + gRPC + whisper.cpp) the platform builds on |
---
## Prerequisites
- **Docker** + **Docker Compose v2** (Docker Desktop on macOS/Windows, or Docker Engine + the Compose plugin on Linux)
- **Git** (the one-line installer also works with `curl` + `tar` when git is missing)
- **8 GB RAM** minimum (16 GB recommended once you add the `local-ai` profile)
- **~4 GB free disk** for the standard install (includes file work + spoken answers; +~1 GB for `local-ai`, +~14 GB if you also enable the local chat model)
- A few host ports must be free. The list, and how to change one without editing the Compose file, is in [Installation — Port conflicts](docs/INSTALLATION.md#port-conflicts).
> **Apple Silicon (M1–M4) Macs — build the backend image, don't pull it.** The three-step start above already does this: `make up` builds the backend and worker locally from a multi-arch base image, so PHP/FrankenPHP runs **natively on `arm64`** with no emulation tax. That is by far the fastest setup, and it is the default — you don't have to do anything special. (The published `ghcr.io/metadist/synaplan` image is multi-arch too, so pulling it also runs natively.) The first local build takes a few minutes; every later start is a cache hit. Two optional dev tools (phpMyAdmin, MailHog) are still amd64-only upstream images — if you keep them, enable **Docker Desktop → Settings → General → "Use Rosetta for x86/amd64 emulation on Apple Silicon"** (macOS 13+) so those two emulate quickly.
---
## Install Options
| Mode | Command | Size | Best For |
|------|---------|------|----------|
| **One-liner** | `curl -fsSL https://raw.githubusercontent.com/metadist/synaplan/main/install.sh \| bash` | ~4 GB | Easiest start — checks prerequisites, fetches, and starts the standard stack (`--mode server` available for production) |
| **Standard** | `make up` | ~4 GB | Local try-out: chat, file work, spoken answers — status page first, then the rest; add one provider key and it works |
| **+ local AI** | `COMPOSE_PROFILES=local-ai make up` | ~5 GB | Adds Ollama and the `bge-m3` embedding model on your own hardware (local chat model optional, +~14 GB) |
| **Production** | `install.sh --mode server` or `deploy/` compose + scripts | published image | Self-host on a Linux server — see [Installation](docs/INSTALLATION.md) |
| **Kubernetes** | [synaplan-charts](https://github.com/metadist/synaplan-charts) | published image | Helm-based cluster deployments for partners and enterprises |
A plain `docker compose up -d` starts the same stack but `:5173` stays silent until every image is pulled — `make up` exists so the status page answers within seconds.
No AI weights are downloaded by default, so the first boot is dominated by the Docker images and `npm ci`. `COMPOSE_PROFILES=local-ai` is the same switch a self-hosted install uses in `deploy/.env`, and it pulls the local embedding model (`bge-m3`, ~1 GB) in the background for RAG and semantic search; progress is shown in the app.
Prefer the shell to the UI for provider keys? Keys in `backend/.env` still work — the backend reads that file when the container starts and imports the key into the encrypted store on first use. Write the key before starting, or restart the containers afterwards:
```bash
echo "GROQ_API_KEY=your_key" >> backend/.env
make up
# already running? pick up the new key with:
# docker compose restart backend worker
```
---
## Access
Open **<http://localhost:5173>**. The API is at <http://localhost:8000>, the API docs at <http://localhost:8000/api/doc>. phpMyAdmin, MailHog, Qdrant, Tika, Ollama and TTS: [Installation — Development service URLs](docs/INSTALLATION.md#development-service-urls).
**Default Login Credentials:**
| Email | Password | Level |
|-------|----------|-------|
| admin@synaplan.com | admin123 | ADMIN |
| demo@synaplan.com | demo123 | PRO |
| test@example.com | test123 | NEW (unverified) |
---
## Features
- **AI Chat** — Ollama, OpenAI, Anthropic, Gemini, Groq, Mistral, xAI, TrustedTokens (DE), A2Agent (CN), HuggingFace ([provider list](#ai-providers--models))
- **Self-aware assistant** — Ask "What can you do here?" or type `/help`; the AI assistant answers from this installation's live capabilities, not a generic brochure
- **Multi-Task DAG Routing** — An AI planner decomposes complex requests into a directed task graph (extract → summarize → generate → reply), routes each step to the model that fits it, and streams live task cards while the steps execute — cheaper models for simple steps means fewer wasted tokens
- **RAG Search** — Semantic document search with MariaDB VECTOR or Qdrant
- **Chat Widget** — Embed on any website ([widget guide](https://docs.synaplan.com/index.php/widget))
- **Mobile Apps** — Chat, documents and voice on iPhone and Android, pointed at web.synaplan.com or at your own server ([App Store](https://apps.apple.com/app/id6784278288?ct=github-readme) · [Google Play](https://play.google.com/store/apps/details?id=com.synaplan.app&referrer=utm_source%3Dgithub-readme))
- **Synaplan Desktop** — Pair a computer and run skills on it. Open **Channels → Synaplan Desktop**. No installer yet ([synaplan-desktop](https://github.com/metadist/synaplan-desktop))
- **AI assistants** — Saved recipes (instructions, knowledge folders, tools, triggers) that you publish in versions ([assistants](https://docs.synaplan.com/assistants))
- **Tools & approvals** — One tool registry; write-class actions pause under **Approvals** ([tools](https://docs.synaplan.com/tools-and-approvals))
- **Users & groups** — Share folders, chats, assistants and tasks; **Operate → Users** ([people](https://docs.synaplan.com/people-and-groups))
- **File work** — Short Python or Node runs on *copies* of files you picked, in an isolated sidecar ([guide](docs/COMPUTE.md))
- **Live Support** — Realtime WebSocket layer (Centrifugo + Redis): human takeover of widget chats, typing indicators, operator notifications ([realtime guide](docs/REALTIME.md))
- **WhatsApp** — Meta Business API integration
- **Email** — AI-powered email responses, plus live mailbox search (IMAP and Microsoft 365)
- **Connections** — Microsoft 365, Dropbox, Nextcloud / ownCloud / WebDAV, CalDAV — read mail, file results, write calendar events ([connections guide](docs/CONNECTIONS.md))
- **Saved Tasks** — Pin a multi-step plan and run it on demand or on a schedule, with a **Steps** editor and webhook trigger (**Manage → Automations → Saved Tasks**)
- **Watched pages** — Save a URL, compare it on a schedule, and mail the diff when it changes
- **Audio** — Whisper transcription (input) + optional [synaplan-tts](https://github.com/metadist/synaplan-tts) (output; five baked voices, UI language selects the voice)
- **Documents** — PDF, Word, Excel, images with OCR; the assistant can also build and revise Office files; optional Collabora CODE sidecar for thumbnails, PDF export, preview and combine ([office documents](https://docs.synaplan.com/index.php/office-documents))
- **AI Memories** — User profiling with Qdrant vector search
- **Feedback System** — Feedback capture and analysis powered by Qdrant
- **Plugins** — Non-invasive plugin system ([plugin guide](https://docs.synaplan.com/index.php/plugins))
- **MCP Server** *(early access)* — Connect AI clients (Claude, Cursor, …) over the Model Context Protocol; your RAG and memories become tools at `POST /mcp` ([MCP guide](https://docs.synaplan.com/index.php/mcp))
- **MCP Client** *(early access)* — Connect *your* MCP servers (Jira, Confluence, CRM, wiki, n8n, …) under **Manage → Connections → MCP Servers**. The planner pulls live data via `mcp_fetch` and, when you enable **allow write actions** on that server, can create tickets or pages via `mcp_action` — destructive tools stay refused. SSRF-guarded, per-topic opt-in. Seeded `BCONFIG` flags (`MCP.CLIENT_ENABLED`, `MULTITASK.MCP_FETCH_ENABLED`, `MULTITASK.MCP_ACTION_ENABLED`) turn this on; an explicit `0` row is the operator kill switch. See [docs/MULTITASK_DATA_NODES.md](docs/MULTITASK_DATA_NODES.md)
- **Claude Code & Anthropic-compatible API** — Point Claude Code or any Anthropic-protocol client at your instance (`POST /v1/messages`); configure under **Manage → Developer & devices → Coding clients** ([guide](docs/ANTHROPIC_COMPATIBLE_API.md))
---
## AI Providers & Models
Synaplan is provider-neutral: connect the providers you want in **Operate → AI infrastructure → Providers & keys** (keys are validated live and stored encrypted in the database, active without a restart), or set the env variables below in `backend/.env` — those are read at container start and imported into the encrypted store on first use. Each user picks a different model **per task** (chat, vision, image, video, audio, embeddings) — nothing is hardcoded.
| Provider | Variable in `backend/.env` | Models |
|----------|---------------------------|--------|
| OpenAI | `OPENAI_API_KEY` | GPT-5.6 Sol / Terra / Luna, GPT-5.5 (+ Pro), GPT-5.4 (+ mini), GPT Image, Whisper, text-embedding-3 |
| Anthropic | `ANTHROPIC_API_KEY` | Claude Opus 5, Sonnet 5, Fable 5, Opus 4.8, Haiku 4.5 (chat + vision) |
| Google Gemini | `GOOGLE_GEMINI_API_KEY` | Gemini 3.x / 2.5 chat + vision, Nano Banana (incl. Pro / Lite), Veo 3.1, Gemini TTS |
| Groq | `GROQ_API_KEY` | Qwen 3.6 27B (chat + vision), GPT-OSS 20B/120B, Whisper Large v3 |
| Mistral 🇫🇷 | `MISTRAL_API_KEY` | Mistral Medium 3.5 (+ vision), Mistral Large 3, Mistral Large 4 (+ vision), Voxtral transcription + TTS |
| xAI | `XAI_API_KEY` | Grok 4.7 / 4.6 / 4.5 (+ vision, 500K context), Grok Imagine image + video (incl. Pro / 1.5 tiers) |
| [Meta](https://dev.meta.ai/) | `META_API_KEY` | Muse Spark 1.3, Muse Wonder (+ vision), Muse Image, Muse Voice Transcribe — Meta Model API |
| [Cerebras](https://cloud.cerebras.ai/) | `CEREBRAS_API_KEY` | Qwen 3.8 27B (+ vision), GPT OSS 120B — very fast inference (~2,000–3,000 tokens/s) |
| [TrustedTokens](https://trustedtokens.eu/) 🇩🇪 | `TRUSTEDTOKENS_API_KEY` | GLM 5.2 / 5.3 (+ Flash vision), Chimera, Qwen3.6 35B (+ vision), GPT OSS 120B — sovereign inference on German GPUs (TNG), zero data retention |
| [A2Agent](https://a2agent.me/) 🇨🇳 | `A2AGENT_API_KEY` | Qwen3.8 MAX / Flash (+ vision), DeepSeek V4 Pro / Flash, MiniMax M3 — Chinese frontier models via the A2Agent gateway |
| HuggingFace | `HUGGINGFACE_API_KEY` | Kimi K3 / K2.5 / K2.6 / K2.7 Code (chat + vision) |
| TheHive | `THEHIVE_API_KEY` | Flux Schnell, SDXL |
| Higgsfield | `HIGGSFIELD_API_KEY` + `HIGGSFIELD_API_SECRET` | Soul, Reve, DoP, Kling 2.1 |
| Cloudflare Workers AI | `CLOUDFLARE_ACCOUNT_ID` + `CLOUDFLARE_API_TOKEN` | bge-m3 embeddings (also usable as embedding fallback) |
| Ollama 🇩🇪 self-hosted | `OLLAMA_BASE_URL` (no key) | Any local model — chat, vision, bge-m3 embeddings |
**Transparent pricing.** Every model carries its provider's own rate (USD per 1M tokens in/out, or per image / second / character for media) — no proprietary credit unit in between. The selector shows a Free / Low / Mid / High cost badge next to each model and on every answer, `GET /api/v1/config/models` returns `priceIn` / `priceOut`, and the Statistics page logs the real cost of each call. On the hosted instance at [web.synaplan.com](https://web.synaplan.com/) that same catalog is what your plan meters against; self-hosted with Ollama, the per-token cost is simply zero. Details: [Model pricing & cost transparency](https://docs.synaplan.com/index.php/faq).
> Model catalog changes (new models, retired generations, price updates) ship as seeders, so an existing install is repointed to a supported successor instead of silently keeping a dead model — a retirement records the successor and every install is switched off on the next deploy. See [docs/PRICING_MAINTENANCE.md](docs/PRICING_MAINTENANCE.md).
---
## Lean by design: core vs optional building blocks
`make up` starts a complete platform, but the **core is deliberately small**: the app, its database and Redis. Everything else is a building block that adds one capability and costs RAM. Switch a block on when you need it and off when you don't — Synaplan keeps running either way and simply hides the matching feature. The boot status screen at <http://localhost:5173> lists the live on/off state of every block, and **Operate → System status** (`/admin/features`) does the same after login.
| Block | Gives you | Default | Switch |
|-------|-----------|---------|--------|
| **Core** — `frontend`, `backend`, `worker`, `scheduler`, `db` (MariaDB), `redis` | The app, its API, async jobs, scheduled jobs, storage, cache and queues | always on | — |
| **Ollama** (`ollama`) | Local AI on your hardware: `bge-m3` embeddings for document search, optional local chat (`ENABLE_LOCAL_GPT_OSS=true`) | **off** | `COMPOSE_PROFILES=local-ai make up` — the same switch as `deploy/.env` in production |
| **Qdrant** (`qdrant`) | Vector database for AI memories, feedback analysis and large-scale RAG | on | `docker compose stop qdrant` — document search itself runs on **MariaDB VECTOR** (the default `VECTOR_STORAGE_PROVIDER`), so RAG keeps working; memories pause |
| **Centrifugo** (`centrifugo`) | Live support: human takeover of widget chats, typing indicators, operator notifications ([realtime guide](docs/REALTIME.md)) | on | `REALTIME_ENABLED=false make up` (then `docker compose stop centrifugo`) — the dashboard falls back to plain REST refreshes |
| **Apache Tika** (`tika`) | Text extraction from PDF, Word, Excel and 1000+ formats for RAG | on | `docker compose stop tika` — uploads then index plain text / OCR only |
| **Collabora CODE** (`collabora`) | Office files: thumbnails, “Download as PDF”, inline preview, “Combine as PDF” (~2 GB RAM) — [details](docs/INSTALLATION.md#optional-office-conversion-collabora) | **off** | `docker compose --profile office up -d` |
| **Docling** (`docling`) | Layout-aware extraction (tables, headings) in front of Tika — [module](https://docs.synaplan.com/modules/docling) | **off** | `docker compose --profile docling up -d` |
| **SearXNG** (`searxng`) | Self-hosted web search so queries stay on your network — [module](https://docs.synaplan.com/modules/searxng) | **off** | `docker compose --profile searxng up -d` |
| **File work** (`compute`) | Short Python / Node jobs on copies of files you pick — [details](docs/INSTALLATION.md#file-work-secure-compute) | **on** | `COMPUTE_URL=disabled make up` |
| **Text-to-speech** (`tts`) | Spoken answers, five built-in voices — [details](#text-to-speech) | **on** | `docker compose stop tts` |
| **Keycloak** (`keycloak`) | SSO test realm for OIDC development ([configuration](docs/CONFIGURATION.md)) | **off** | `docker compose --profile oidc up -d` |
**Keep a default-on block off across restarts.** `docker compose stop` is undone by the next `up -d`. To make a block opt-in permanently, give it a profile in a `docker-compose.override.yml` (not tracked by git) — plain `up -d` then skips it, `--profile optional` brings it back:
```yaml
services:
qdrant:
profiles: [optional]
```
Production follows the same rule set: [`deploy/compose.yaml`](deploy/README.md) always starts web/worker/scheduler plus db/redis/centrifugo/tika/qdrant and spoken answers, with `office`, `local-ai` and `compute` as profiles (`COMPOSE_PROFILES=office,local-ai,compute` in `deploy/.env`). Kubernetes installs wire the same services via [synaplan-charts](https://github.com/metadist/synaplan-charts). The other dev-only containers (`phpmyadmin`, `mailhog`, `frontend-widgets`, `startup-notes`) never ship to production.
---
## Realtime & Background Processing
Both compose files also start four internal services (no host ports, no setup needed):
| Service | Role |
|---------|------|
| `redis` | Mandatory shared infrastructure: cache, sessions, locks, rate limits, message queues (Redis Streams), Centrifugo engine |
| `centrifugo` | WebSocket gateway for realtime features (live chat takeover, typing indicators, operator notifications) — browsers connect same-origin via `/connection/websocket` |
| `worker` | Symfony Messenger consumer that executes async jobs (AI processing, document indexing, widget crawling) |
| `scheduler` | Ticks every 60 s: saved tasks, media-job reaping, ephemeral-file cleanup, update check |
In a multi-node cluster all nodes share one Redis, so WebSocket events published on one node reach browsers connected to any other. Details: [docs/REALTIME.md](docs/REALTIME.md).
---
## Text-to-Speech
Voice output starts with `make up` — [synaplan-tts](https://github.com/metadist/synaplan-tts), image [`ghcr.io/metadist/synaplan-tts`](https://github.com/metadist/synaplan-tts/pkgs/container/synaplan-tts). The image already contains **five Piper voices** (English, German, Spanish, French, Turkish). Stop the `tts` container to hide the speaker control.
```bash
# Already running after `make up`. Standalone on another machine:
docker run -d --name synaplan-tts -p 127.0.0.1:10200:10200 ghcr.io/metadist/synaplan-tts:latest
```
The backend looks at `SYNAPLAN_TTS_URL` (compose default `http://tts:10200`).
**The UI language selects the voice.** Chat sends the active frontend locale (`en` / `de` / `es` / `fr` / `tr`); if the backend detects a different reply language, that wins. Piper then maps the short code to the matching baked voice (German UI → kerstin, Spanish → davefx, …). There is no separate voice picker. Add more Piper models by dropping `.onnx` + `.onnx.json` into the extra-voices volume — see [synaplan-tts README](https://github.com/metadist/synaplan-tts#adding-more-voices) and [docs.synaplan.com/tts](https://docs.synaplan.com/index.php/tts).
---
## Office documents
Thumbnails, PDF export, inline preview and “Combine as PDF” need an optional Collabora CODE sidecar. It is off by default, so `make up` does not pull it. Chat and DOCX / XLSX / PPTX generation work without it. Setup, including why `OFFICE_CONVERT_URL` does not belong in `backend/.env`: [Installation — Optional office conversion](docs/INSTALLATION.md#optional-office-conversion-collabora).
---
## File work
The assistant can run a short Python or Node program on copies of files you already picked. `make up` starts it. The dev token, and how to turn the sidecar off, are in [Installation — File work](docs/INSTALLATION.md#file-work-secure-compute).
---
## Common Commands
```bash
# Startup progress ("please wait..." notes + READY message)
docker compose logs -f startup-notes
# Logs
docker compose logs -f backend
# Restart
docker compose restart backend
# Reset database
docker compose down -v && make up
# Run tests
make test
# Code quality
make lint
```
---
## Documentation
User-facing & API docs live at **[docs.synaplan.com](https://docs.synaplan.com/)**. Source: [`metadist/synaplan-docs`](https://github.com/metadist/synaplan-docs).
In-repo guides (for developers working on this codebase):
| Guide | Description |
|-------|-------------|
| [Installation](docs/INSTALLATION.md) | Local development stack and production self-hosting (`deploy/`) |
| [Configuration](docs/CONFIGURATION.md) | Environment variables, API keys |
| [Feature flags](docs/FEATURE_FLAGS.md) | Every wave feature (people & sharing, assistants, tools, saved-task steps, desktop, file work, …): admin toggle, `FEATURE_*` env pin, defaults |
| [File work / compute](docs/COMPUTE.md) | Optional sidecar: flags, compose profile, quotas, workspaces |
| [Connections](docs/CONNECTIONS.md) | Microsoft 365, Dropbox, Nextcloud / WebDAV, CalDAV, Jira / Confluence |
| [AI Model Pricing](docs/PRICING_MAINTENANCE.md) | Model catalog, provider prices, retiring a model |
| [Development](docs/DEVELOPMENT.md) | Commands, testing, architecture |
| [Realtime / WebSockets](docs/REALTIME.md) | Centrifugo + Redis realtime layer, multi-node deployment |
| [Observability](docs/OBSERVABILITY.md) | Request correlation ids, redacted event ring, admin logs API |
| [Office documents](https://docs.synaplan.com/index.php/office-documents) | Optional Collabora CODE sidecar (PDF export, previews, convert-to) |
| [RAG System](docs/RAG.md) | Document search and processing |
| [Chat Widget](docs/WIDGET.md) | Embed chat on websites |
| [WhatsApp](docs/WHATSAPP.md) | Meta Business API setup |
| [Email](docs/EMAIL.md) | Email channel integration |
| [Anthropic-compatible API](docs/ANTHROPIC_COMPATIBLE_API.md) | Claude Code / Messages API gateway (`POST /v1/messages`) |
| [Secure compute (user docs)](https://docs.synaplan.com/modules/compute) | What people see: File work card, Workspace, quotas |
## Related Repositories
| Repo | Purpose |
|------|---------|
| [synaplan](https://github.com/metadist/synaplan) | Main app (this repo) |
| [synaplan-docs](https://github.com/metadist/synaplan-docs) | Public docs site (docs.synaplan.com) |
| [Synamail](https://github.com/metadist/Synamail) | Outlook add-in |
| [synaplan-desktop](https://github.com/metadist/synaplan-desktop) | Synaplan Desktop (Windows, macOS, Linux). No installer yet; build from source. |
| [synaplan-apps](https://github.com/metadist/synaplan-apps) | iOS and Android apps — [App Store](https://apps.apple.com/app/id6784278288) · [Google Play](https://play.google.com/store/apps/details?id=com.synaplan.app) |
| [synaplan-nextcloud](https://github.com/metadist/synaplan-nextcloud) | Nextcloud integration |
| [synaplan-opencloud](https://github.com/metadist/synaplan-opencloud) | OpenCloud integration |
| [synaplan-tts](https://github.com/metadist/synaplan-tts) | Optional Piper TTS — [image](https://github.com/metadist/synaplan-tts/pkgs/container/synaplan-tts) with 4 baked voices |
| [synaplan-sortx](https://github.com/metadist/synaplan-sortx) | Document-sorting plugin + local tool |
| [synaplan-charts](https://github.com/metadist/synaplan-charts) | Helm charts for Kubernetes |
| [synaplan-platform](https://github.com/metadist/synaplan-platform) | Production deployment configs |
---
## Project Structure
```
synaplan/
├── backend/ # Symfony PHP API
├── frontend/ # Vue.js SPA
├── docs/ # Developer documentation
├── deploy/ # Production self-host compose + lifecycle scripts
├── sidecars/ # Optional sidecars (secure compute)
├── _docker/ # Docker configs
└── plugins/ # Plugin system
```
---
## Star history
<a href="https://star-history.com/#metadist/synaplan&Date">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=metadist/synaplan&type=Date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=metadist/synaplan&type=Date" />
<img alt="Star history of metadist/synaplan" src="https://api.star-history.com/svg?repos=metadist/synaplan&type=Date" width="720">
</picture>
</a>
## Community & Support
- **[Discord](https://discord.com/invite/kQB3eDjWfF)** — chat with the team and community; the fastest place for self-hosting and configuration questions
- **[GitHub Issues](https://github.com/metadist/synaplan/issues)** — bugs and feature requests
- **[Security policy](SECURITY.md)** — how to report a vulnerability privately, and what happens next
- **[www.synaplan.com](https://www.synaplan.com)** — product, hosting and enterprise contact
## Contributing
See [CONTRIBUTING.md](CONTRIBUTING.md). [AGENTS.md](AGENTS.md) is the guide for coding agents working in this repository.
---
## License
[Apache-2.0](LICENSE)
<p align="center">
<a href="https://osb-alliance.de/" target="_blank" rel="noopener noreferrer"><img src="docs/images/osba-member.png" alt="OSBA" width="180" height="90"></a>
</p>
This server cannot be deployed