Drop-in HTTP proxy for Ollama with priority queuing, per-client auth, and model-aware failover
-
Updated
Jun 23, 2026 - Python
#
ollama-proxy
Here are 4 public repositories matching this topic...
A proxy server written entirely in Go (with no external dependencies) that translates Ollama API requests into an OpenAI-compatible API format. It allows native Ollama clients (Ollie, Enchanted, CLI) to transparently work with models hosted on Open WebUI. It supports streaming, multimodal requests (images), three-level caching, AES-256-GCM session
go golang ai api-gateway proxy self-hosted reverse-proxy zero-dependencies translation-layer openai-api llm ollama open-webui ollama-proxy
-
Updated
Mar 15, 2026 - Go
ai-security llm-as-a-judge llm-guardrails structured-outputs prompt-injection-defense ollama-proxy safety-middleware
-
Updated
Jun 23, 2026 - Python
Translate Ollama API calls to OpenAI format and enable Ollama clients to access models hosted on Open WebUI without client changes.
python http ai rest-api proxy proxy-server self-hosted fastapi translation-layer openai-api ollama-webui ollama-api open-webui anthropic-api ollama-proxy openwebui-api
-
Updated
Jul 13, 2026 - Go
Improve this page
Add a description, image, and links to the ollama-proxy topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the ollama-proxy topic, visit your repo's landing page and select "manage topics."