# 奥德修斯--自主托管的 AI 工作区

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：Dzheky
- 发布时间：2026-06-01 08:11
- AIHOT 分数：58
- AIHOT 链接：https://aihot.virxact.com/items/cmpugzndo03l7slaglkugatw5
- 原文链接：https://github.com/pewdiepie-archdaemon/odysseus

## AI 摘要

奥德修斯是一个自主托管的 AI 工作区项目，其源代码已在 GitHub 上公开。

## 正文

Odysseus

Branch note: dev is the default branch and contains the latest development changes, but it may be unstable. For the more stable curated branch, use main.

Branch note: dev is the default branch and contains the latest development changes, but it may be unstable. For the more stable curated branch, use main.

dev

main

─────────────────────────────────────────────── ⊹ ࣪ ˖ ૮( ˶ᵔ ᵕ ᵔ˶ )っ Odysseus vers. 1.0 ───────────────────────────────────────────────

─────────────────────────────────────────────── ⊹ ࣪ ˖ ૮( ˶ᵔ ᵕ ᵔ˶ )っ Odysseus vers. 1.0 ───────────────────────────────────────────────

A self-hosted AI workspace -- meant to be the self-hosted version of the UI experience you get from ChatGPT and Claude. But with more jank and fun. Running on your own hardware, with your own data -- local-first, privacy-first, and no trojan.

Features

Chat -- chat with any local model or API; adding them is super simple. vLLM · llama.cpp · Ollama · OpenRouter · OpenAI · GitHub Copilot

Agent -- hand it tools and let it run the whole task itself. built on opencode · MCP · web · files · shell · skills · memory

Cookbook -- Scans your hardware, recommends models, click to download and serve.. easy! built on llmfit · VRAM-aware · GGUF / FP8 / AWQ · fit scoring · vLLM / llama.cpp serving

Deep Research -- multi-step runs that gather, read, and synthesize sources into a nice visual report. adapted from Tongyi DeepResearch

Compare -- a fun tool to compare models side by side. Test completely blind, no bias! multi-model · blind test · synthesis

Documents -- YOU write the text, AI is there to assist, not the opposite. multi-tab editor · markdown · HTML · CSV · syntax highlighting · AI edits · suggestions

Memory / Skills -- Persistent memory and skills, your agent evolves over time as it better understands you and your tasks! ChromaDB · fastembed (ONNX) · vector + keyword retrieval · import/export

Email -- IMAP/SMTP inbox with AI triage built in: urgency reminders, auto-tag, auto-summary, auto-reply drafts, auto-spam. IMAP · SMTP · per-account routing · CalDAV-aware

Notes & Tasks -- Quick notes with reminders, a todo list, and scheduled tasks the agent can act on. note pings · checklist · cron-style tasks · ntfy / browser / email channels

Calendar -- Local-first calendar with CalDAV sync to Radicale / Nextcloud / Apple / Fastmail. CalDAV pull · .ics import/export · per-calendar colors · agent-aware

Works on mobile -- looks and runs great on your phone, not just desktop. responsive · installable (PWA) · touch gestures

Extras -- more to explore, happy if you give it a go! image editor · theme editor · file uploads (vision + PDF) · web search · presets · sessions · 2FA

Demo

A full, hover-to-play tour lives on the landing page (docs/index.html).

docs/index.html

Chat & Agents

Deep Research

Compare

Documents

Notes & Tasks

Quick Start

Defaults work out of the box: clone, run, then configure models/search/email inside Settings. Only edit .env for deployment-level overrides like APP_BIND, APP_PORT, AUTH_ENABLED, DATABASE_URL, or a pre-seeded admin password.

.env

APP_BIND

APP_PORT

AUTH_ENABLED

DATABASE_URL

On first setup, Odysseus creates an admin account (admin unless ODYSSEUS_ADMIN_USER is set) and prints a temporary password in the terminal. For Docker installs, the same line is in docker compose logs odysseus. Use that for the first login, then change it in Settings.

admin

ODYSSEUS_ADMIN_USER

docker compose logs odysseus

Contributing? See CONTRIBUTING.md for setup, testing, and pull request guidelines.

Docker (recommended)

git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus cp .env.example .env # optional, but recommended for explicit defaults docker compose up -d --build

To include optional extras in the image (PDF viewer, Office extraction; includes AGPL PyMuPDF), build with docker compose build --build-arg INSTALL_OPTIONAL=true before up.

docker compose build --build-arg INSTALL_OPTIONAL=true

up

Open http://localhost:7000 when the containers are healthy. Docker Compose binds the web UI to 127.0.0.1 by default. If the port is taken, set APP_PORT=7001 in .env and recreate the container. Set APP_BIND=0.0.0.0 only when you intentionally want LAN/reverse-proxy access.

http://localhost:7000

127.0.0.1

APP_PORT=7001

.env

APP_BIND=0.0.0.0

Native Linux / macOS

git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus python3 -m venv venv source venv/bin/activate pip install -r requirements.txt python setup.py python -m uvicorn app:app --host 127.0.0.1 --port 7000

Requirements: Python 3.11+. Cookbook also needs tmux for background model downloads and serves. The app itself is lightweight; local model serving is the heavy part and depends on the model, runtime, GPU, and VRAM, so small hosts can connect to API or remote model servers instead. Use --host 0.0.0.0 only when you intentionally want LAN/reverse-proxy access.

tmux

--host 0.0.0.0

Apple Silicon

Docker on macOS cannot use the Metal GPU. For GPU-accelerated Cookbook on an M-series Mac, run Odysseus natively:

git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus ./start-macos.sh

It launches at http://127.0.0.1:7860. To expose it to your phone over a trusted LAN/VPN such as Tailscale, bind all interfaces:

http://127.0.0.1:7860

ODYSSEUS_HOST=0.0.0.0 ./start-macos.sh # then open http://:7860

The script also reads .env at startup, so APP_BIND=0.0.0.0 and APP_PORT set there are picked up automatically without a command-line override each run.

.env

APP_BIND=0.0.0.0

APP_PORT

Keep AUTH_ENABLED=true (the default) before binding outside loopback. Do not expose this port directly to the public internet. To build a clickable app wrapper:

AUTH_ENABLED=true

./build-macos-app.sh

Docker bundled services. Compose starts Odysseus, ChromaDB, SearXNG, and ntfy. Odysseus and the bundled service ports bind to 127.0.0.1 by default, so they are reachable from the host but not exposed to your LAN/public internet unless you opt in.

127.0.0.1

Cookbook storage in Docker. Downloads live in ./data/huggingface (~/.cache/huggingface in the container). Cookbook-installed Python CLIs and serve engines live in ./data/local (~/.local in the container), so they survive container recreation.

./data/huggingface

~/.cache/huggingface

./data/local

~/.local

Remote servers. In Cookbook -> Settings -> Servers, generate the Odysseus SSH key and add the public key to the remote server's ~/.ssh/authorized_keys. From the host you can also run:

~/.ssh/authorized_keys

ssh-copy-id -i data/ssh/id_ed25519.pub user@server

Docker GPU overlays. CPU-only users can skip this section. Cookbook can only detect GPUs that Docker exposes to the container — if the host runtime or device passthrough is not configured, Cookbook sees the iGPU, another card, or CPU instead of your intended GPU.

For NVIDIA, scripts/check-docker-gpu.sh diagnoses GPU passthrough and can optionally install the host runtime or update .env.

scripts/check-docker-gpu.sh

.env

# Read-only diagnostic (default — installs nothing, never edits .env): scripts/check-docker-gpu.sh # Print OS-specific install commands without running them: scripts/check-docker-gpu.sh --print-install-commands # Install NVIDIA Container Toolkit on Ubuntu/Debian (requires sudo): scripts/check-docker-gpu.sh --install-nvidia-toolkit # Write COMPOSE_FILE to .env (only when GPU passthrough is confirmed working): scripts/check-docker-gpu.sh --enable-nvidia-overlay # Full assisted setup — install toolkit, then enable overlay if passthrough works: scripts/check-docker-gpu.sh --install-nvidia-toolkit --enable-nvidia-overlay

Safety notes:

The app never installs host GPU runtime automatically.

The app never edits .env automatically.

.env

.env is only modified when --enable-nvidia-overlay is explicitly passed, and only after GPU passthrough succeeds. --yes skips prompts but does not bypass the passthrough gate.

.env

--enable-nvidia-overlay

--yes

.env.bak.* backups created by --enable-nvidia-overlay are ignored by Git and the Docker build context.

.env.bak.*

--enable-nvidia-overlay

To enable manually without the script, add this to .env:

.env

COMPOSE_FILE=docker-compose.yml:docker/gpu.nvidia.yml

AMD / ROCm. AMD setup is read-only diagnostic plus manual .env edit. Run:

.env

scripts/check-docker-amd-gpu.sh

Then add the reported values to .env, replacing RENDER_GID with your host's numeric render group id:

.env

RENDER_GID

COMPOSE_FILE=docker-compose.yml:docker/gpu.amd.yml RENDER_GID=989

For NVIDIA/AMD GPU support, also read the comments in the selected overlay file: docker/gpu.nvidia.yml or docker/gpu.amd.yml.

Stack-management UIs (Portainer, Coolify, Dockhand, etc.). These tools often accept only a single Compose file and do not reliably honor COMPOSE_FILE or multiple -f overlays. CLI users should keep using the COMPOSE_FILE overlay workflow above. For stack UIs, point the stack at one of the standalone files instead, which bundle the base stack plus the GPU settings:

COMPOSE_FILE

-f

COMPOSE_FILE

docker-compose.gpu-nvidia.yml — still requires the NVIDIA Container Toolkit on the host.

docker-compose.gpu-nvidia.yml

docker-compose.gpu-amd.yml — still requires host ROCm/kfd/DRI setup, the video/render group membership, and RENDER_GID when needed.

docker-compose.gpu-amd.yml

video

render

RENDER_GID

The base docker-compose.yml plus the docker/gpu.*.yml overlays remain the source of truth; the standalone files mirror them for single-file deployments.

docker-compose.yml

docker/gpu.*.yml

Verify after enabling either overlay:

docker compose exec odysseus nvidia-smi -L # NVIDIA docker compose exec odysseus sh -lc 'test -e /dev/kfd && test -d /dev/dri && ls -l /dev/kfd /dev/dri/renderD*' # AMD

GPU passthrough ≠ llama.cpp CUDA. nvidia-smi passing inside the container confirms Docker GPU access, but llama.cpp also needs cudart and the CUDA Toolkit at runtime. If Cookbook logs show Unable to find cudart library, Could NOT find CUDAToolkit, CUDA Toolkit not found, or tensors/layers assigned to CPU, that is a Cookbook/llama.cpp build issue — not a Docker passthrough failure. Reinstall the serve engine via Cookbook → Dependencies to get a CUDA-enabled build. The same split applies to AMD/ROCm: seeing /dev/kfd and /dev/dri inside the container confirms device passthrough, not ROCm userspace or a ROCm-enabled vLLM/llama.cpp build. rocm-smi and rocminfo are not expected inside the slim Odysseus image.

GPU passthrough ≠ llama.cpp CUDA. nvidia-smi passing inside the container confirms Docker GPU access, but llama.cpp also needs cudart and the CUDA Toolkit at runtime. If Cookbook logs show Unable to find cudart library, Could NOT find CUDAToolkit, CUDA Toolkit not found, or tensors/layers assigned to CPU, that is a Cookbook/llama.cpp build issue — not a Docker passthrough failure. Reinstall the serve engine via Cookbook → Dependencies to get a CUDA-enabled build.

nvidia-smi

cudart

Unable to find cudart library

Could NOT find CUDAToolkit

CUDA Toolkit not found

The same split applies to AMD/ROCm: seeing /dev/kfd and /dev/dri inside the container confirms device passthrough, not ROCm userspace or a ROCm-enabled vLLM/llama.cpp build. rocm-smi and rocminfo are not expected inside the slim Odysseus image.

/dev/kfd

/dev/dri

rocm-smi

rocminfo

Ollama with Docker. If Ollama runs on the host, add this endpoint in Settings:

http://host.docker.internal:11434/v1

http://host.docker.internal:11434/v1

Ollama must listen outside its own loopback interface:

OLLAMA_HOST=0.0.0.0:11434 ollama serve

This connects Odysseus in Docker to an Ollama server that is already running on your host machine; it does not start Ollama inside the container. host.docker.internal is Docker's hostname for the host machine from inside the container. Cookbook Serve is a separate workflow for serving downloaded models through Odysseus/llama.cpp, so Windows users with an existing Ollama install usually only need to add the endpoint in Settings.

host.docker.internal

Useful checks.

docker compose ps docker compose logs --tail=120 odysseus docker compose logs odysseus | grep -E 'ChromaDB|MemoryVectorStore|DEGRADED'

macOS details. start-macos.sh installs Homebrew deps, creates the venv, runs setup, and starts uvicorn on port 7860 because AirPlay often holds 7000. It uses llama.cpp/Ollama for Metal. vLLM/SGLang are CUDA/ROCm-only and do not run on macOS. MLX-only models are not served by Odysseus.

start-macos.sh

7860

7000

Native Windows

One-command launcher (creates the venv, installs deps, runs setup, starts the server; safe to re-run):

git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus powershell -ExecutionPolicy Bypass -File .\launch-windows.ps1

Or do it by hand:

git clone https://github.com/pewdiepie-archdaemon/odysseus.git cd odysseus py -3.11 -m venv venv venv\Scripts\Activate.ps1 pip install -r requirements.txt python setup.py python -m uvicorn app:app --host 127.0.0.1 --port 7000

If python points at an older interpreter, use py -3.12 (or another installed 3.11+ version) for the venv step.

python

py -3.12

Requirements: Python 3.11+. The core app (chat, agent, memory, documents, email, calendar, deep research) runs fully native. For full Cookbook background model downloads and the agent shell tool, also install Git for Windows (provides bash.exe). Local GPU serving of vLLM/SGLang needs Linux/WSL2; for a local model on Windows, Ollama is the easiest path — point Odysseus at http://localhost:11434/v1 in Settings.

bash.exe

http://localhost:11434/v1

Open http://localhost:7000, log in with the generated admin password, and configure everything else inside Settings.

http://localhost:7000

Troubleshooting & Advanced Setup

chromadb-client conflicts with embedded ChromaDB

chromadb-client

If chromadb-client (the lightweight HTTP-only package) is installed alongside the full chromadb package, Odysseus starts but ChromaDB silently falls back to HTTP-only mode and fails.

chromadb-client

chromadb

Fix: uninstall chromadb-client and force-reinstall the full package:

chromadb-client

./venv/bin/pip uninstall chromadb-client -y ./venv/bin/pip install --force-reinstall chromadb

HTTPS + LAN/Tailscale exposure

To expose Odysseus on a local network or Tailscale with HTTPS:

Change the bind address to 0.0.0.0 in .env (APP_BIND=0.0.0.0 or ODYSSEUS_HOST=0.0.0.0).

0.0.0.0

.env

APP_BIND=0.0.0.0

ODYSSEUS_HOST=0.0.0.0

Generate a locally-trusted cert for your LAN/Tailscale IPs using mkcert: mkcert -install mkcert -cert-file cert.pem -key-file key.pem 192.168.1.100 tailscale-ip

mkcert -install mkcert -cert-file cert.pem -key-file key.pem 192.168.1.100 tailscale-ip

Run uvicorn with the generated certs: python -m uvicorn app:app --host 0.0.0.0 --port 7000 --ssl-certfile=cert.pem --ssl-keyfile=key.pem

uvicorn

python -m uvicorn app:app --host 0.0.0.0 --port 7000 --ssl-certfile=cert.pem --ssl-keyfile=key.pem

Install the mkcert CA on any other device you want to access Odysseus from (e.g., for iOS, email the rootCA.pem to yourself, install the profile, and trust it in Certificate Trust Settings).

mkcert

rootCA.pem

Optional Dependencies

requirements-optional.txt contains packages that unlock extra features. It is not installed by default.

requirements-optional.txt

Package Feature unlocked faster-whisper Local speech-to-text (microphone -> text) via the "local" STT provider. ddgs DuckDuckGo as a search provider option. PyMuPDF PDF page rendering in the side viewer panel and form-filling. (Note: AGPL-3.0) markitdown Office/EPUB document text extraction (converts .docx/.xlsx/.pptx/.xls/.epub to Markdown).

faster-whisper

ddgs

PyMuPDF

markitdown

Outlook / Office 365 email