Odysseus v1 Private AI Workspace

Deploys Odysseus 1.0.3, an open-source self-hosted AI workspace with chat, agents, deep research, memory, documents, notes and tasks. Includes ChromaDB, SearXNG, ntfy and a CPU Ollama model, so it can chat without an API key.

What you get

  • The official Odysseus image pinned by digest, with a login and a generated admin password; data on a volume at /app/data
  • ChromaDB for memory and document retrieval, and SearXNG as a private web-search backend
  • ntfy for reminders and alerts, public but with anonymous access denied
  • Ollama on CPU with qwen3:1.7b and a tuned qwen3-cpu:1.7b variant (thinking off), about 1.4 GB downloaded at first boot
  • Optional API provider settings (LLM_PROVIDER_API_KEY, base URL, model) registered on first boot

Good for

  • A private ChatGPT-style workspace for a person or small team
  • A research assistant that searches the web through your own SearXNG and writes cited reports
  • A personal knowledge base answered from uploaded documents
  • Notes, tasks and reminders delivered to your phone through ntfy

Services in this template

  • Ollama · from baranberkay96/odysseus-railway
  • Odysseus · from baranberkay96/odysseus-railway
  • SearXNG · from baranberkay96/odysseus-railway
  • ChromaDB · image chromadb/chroma:1.5.9@sha256:1e0b73a187a28757c572acba508c46f48c9e8b0acaf5c20e6d95cdedce1acdf6
  • ntfy · from baranberkay96/odysseus-railway

Questions people ask

How do I log in?

Open the Odysseus URL and sign in as admin with ODYSSEUS_ADMIN_PASSWORD from the Odysseus service Variables tab, then change it in Settings. After a few minutes pick qwen3-cpu:1.7b in the model menu, not the plain qwen3:1.7b. For ntfy, sign in with NTFY_ADMIN_USER and NTFY_ADMIN_PASSWORD from the ntfy service.

How fast is the bundled model?

It runs on CPU without a GPU, so answers are slower and weaker than hosted models. The template notes estimate a short answer in roughly 10 to 40 seconds on 8 vCPUs, with agent turns using tools or search taking longer; this is an estimate, not a measurement. For faster answers add an API provider key.

What drives the cost?

Five services run continuously. Ollama's CPU and memory use are the largest, since model speed depends on vCPUs; Odysseus, ChromaDB, SearXNG and ntfy are lighter. Each stateful service has a volume. Provider API usage is billed by the provider.

How do I upgrade or scale?

The Odysseus tag and digest are in services/odysseus/Dockerfile. Back up the Odysseus volume, change them and redeploy; keep the digest because upstream's latest tag moves. Odysseus keeps SQLite and files on its volume, so run one replica and raise its RAM or CPU instead.

Any licence notes?

Odysseus and SearXNG are AGPL-3.0 and run here unmodified. ChromaDB and the Qwen3 model are Apache-2.0, Ollama is MIT, and ntfy is Apache-2.0 or GPL-2.0. The login stays enabled on purpose, because the agent can run shell and file tools. This is a community template, not affiliated with the Odysseus project.

Full template README

Deploy and Host Odysseus with Railway

Odysseus is an open-source, self-hosted AI workspace: chat with local or cloud models, agents with tools, deep research, persistent memory, documents, notes, tasks, calendar and email in one web app. This template deploys Odysseus with private web search, a vector store, push alerts and a local model, ready to chat without an API key.

About Hosting Odysseus

Odysseus is a FastAPI application that keeps its data in SQLite and files on disk, stores memory and document vectors in ChromaDB, searches the web through SearXNG and sends reminders through ntfy. Running it well means pinning the app image, giving each stateful service a volume, starting the app only after its vector store is reachable, keeping login enabled because the agent can run shell and file tools, and connecting at least one language model. This community template runs the official Odysseus 1.0.3 image with all four upstream services, adds a CPU Ollama service with a small model, creates the admin account from a generated password, and registers the model, the ntfy integration and your optional API provider on first boot.

Common Use Cases

  • A private ChatGPT-style workspace for a person or small team, with chats and memory kept in your own Railway project
  • Research assistant that searches the web through your own SearXNG instance and writes cited reports
  • Personal knowledge base: upload documents, then ask questions answered from ChromaDB-backed retrieval
  • Notes, tasks and reminders that reach your phone through the bundled, login-protected ntfy server
  • One interface for several providers: the bundled local model plus OpenAI, OpenRouter or any OpenAI-compatible API

Dependencies for Odysseus Hosting

  • Odysseus web app (included, public URL with login)
  • ChromaDB vector store, SearXNG metasearch, ntfy push server and Ollama (included, private except ntfy)
  • Optional: an API key for an OpenAI-compatible provider for faster and stronger models
  • Optional: the ntfy app on Android or iOS to receive alerts on your phone

Deployment Dependencies

Implementation Details

Service Source Purpose
Odysseus ghcr.io/odysseus-dev/odysseus:1.0.3 (digest-pinned) plus a start wrapper Web UI and API on port 7000, healthcheck /api/health, volume /app/data
ChromaDB chromadb/chroma:1.5.9 Vector memory, document retrieval and semantic skills; private, volume /data
SearXNG searxng/searxng:2026.10.13-22c64b8d3 with JSON output enabled Web search for chat and deep research; private
ntfy binwiederhier/ntfy:v2.30.0 with provisioned users Reminder and alert delivery; public URL, anonymous access denied, volume /var/lib/ntfy
Ollama ollama/ollama:0.40.3; pulls qwen3:1.7b and creates the tuned qwen3-cpu:1.7b Local chat model on CPU, threads sized to the service's vCPU limit, thinking off; private, volume /root/.ollama

First login

  1. Optional: paste LLM_PROVIDER_API_KEY (and LLM_PROVIDER_BASE_URL / LLM_PROVIDER_MODEL for providers other than OpenAI) when deploying.
  2. Open the Odysseus URL and sign in as admin with ODYSSEUS_ADMIN_PASSWORD from the Odysseus service's Variables tab. Change the password under Settings.
  3. The first boot downloads the local model (about 1.4 GB). The Ollama endpoint and qwen3-cpu:1.7b appear in the model menu a few minutes after deploy. Pick qwen3-cpu:1.7b rather than the plain qwen3:1.7b, which keeps qwen3's slow reasoning phase.
  4. Alerts: install the ntfy app, add the server https://{ntfy-domain}, sign in with NTFY_ADMIN_USER / NTFY_ADMIN_PASSWORD from the ntfy service, and subscribe to the topic odysseus. Reminders from notes and tasks are delivered there and in the browser. On iPhone, set NTFY_UPSTREAM_BASE_URL to https://ntfy.sh for instant delivery.

Local model speed: the bundled model runs on CPU without a GPU. Expect a short answer in roughly 10 to 40 seconds on 8 vCPUs; agent turns with tools or web search take longer. For fast, stronger answers, set LLM_PROVIDER_API_KEY (plus LLM_PROVIDER_BASE_URL and LLM_PROVIDER_MODEL for providers other than OpenAI) and redeploy Odysseus, or add a provider under Settings. The local model then stays available for private chats.

  • Threads: at every start the Ollama service sizes its thread pool to its CPU quota, at most 8 threads, because more threads than the CPU time actually granted stall generation. Override with OLLAMA_NUM_THREAD.
  • Thinking: qwen3 normally reasons silently before it answers, which on CPU can add a minute or more per answer. qwen3-cpu:1.7b answers directly. To turn reasoning back on, set OLLAMA_THINKING=true on the Ollama service and redeploy it.

Scaling: Odysseus keeps SQLite and files on its volume, so it runs as one replica; raise its RAM or CPU instead. Ollama speed depends on vCPUs; give it more CPU, or set OLLAMA_BASE_MODEL to a larger model (for example qwen3:4b, renaming OLLAMA_DEFAULT_MODEL to match) if you raise its memory. ChromaDB, SearXNG and ntfy are light.

Pinning and upgrades: the Odysseus image tag and digest are in services/odysseus/Dockerfile; the other images are pinned in their Dockerfiles or in the service source. Back up the Odysseus volume, change the tag and digest to a newer release, and redeploy. Upstream's :latest and bare version tags move on every push, so keep the digest.

Why Deploy Odysseus on Railway?

Railway runs the app, its vector store, search engine, notification server and model side by side with private networking, volumes and HTTPS, so you get a complete private AI workspace in one deploy. You pay only for the resources it uses, and you can add API providers or remove the local model at any time.

View Odysseus v1 Private AI Workspace on railway.com

Similar templates

TemplateCategoryDeploymentsDeploys
9Router
Self-hosted AI router for Claude, Gemini, Cursor & OpenAI tools.
AI/ML9,734
flowise-railway
Flowise - low-code LLM apps builder
AI/ML8,512
LibreChat
Open-source ChatGPT clone: multi-model, agents, search, multi-user auth
AI/ML6,762
Hermes Agent by Nous Research
Template for Hermes Agent by Nous Research
AI/ML6,413
OpenClaw
[Homebrew support] The AI that actually does things
AI/ML5,167
Hermes Agent
Self Host Hermes Agent. Autonomous AI agent w/ self-improving, tools & more
AI/ML4,092