Private AI server: local models behind OpenAI-, Ollama- and Anthropic-compatible APIs.
149
Your own private AI server. Run chat, vision, embeddings, reranking, speech-to-text, text-to-speech, image generation and moderation models on your own hardware, behind the API your software already speaks. Nothing leaves your network.
/v1/chat/completions, /v1/responses, /v1/embeddings,
/v1/audio/*, /v1/images/*, /v1/moderations, /v1/batches), plus Ollama's API and Anthropic's Messages API.Product page: https://offlinai.com/offlinai-server.html
The Free plan serves programs on the same machine. On Linux:
docker run -d --name oas --network host -v oas-data:/data offlinai/offlinai-server
# a one-time link to set the console's password
docker exec oas offlinai-server admin bootstrap --url http://127.0.0.1:12436
Then point any OpenAI client at http://127.0.0.1:12436/v1, and open the console to download models.
With a licence that includes network serving, other machines use HTTPS on port 12443:
docker run --rm -v oas-data:/data offlinai/offlinai-server license activate <key>
docker run -d --name oas -p 12443:12443 -v oas-data:/data offlinai/offlinai-server
docker exec oas offlinai-server admin bootstrap --url https://<host>:12443
docker exec oas cat /data/tls/ca.pem # the certificate authority clients install
/data
volume.-e OAE_BACKEND=vulkan -e OAE_IMAGE_BACKEND=vulkan.0.1.0, …) and latest. Linux x86-64./usr/share/doc/offlinai-server inside the image.Content type
Image
Digest
sha256:32a7100ea…
Size
145 MB
Last updated
about 3 hours ago
docker pull offlinai/offlinai-server