Examples

Browse 120 tracked YAML configurations from the v0.8.0 (alpha) Praxis AI source snapshot. Pages and downloads keep the selected version and source commit. Examples may need local services, credentials, or certificates; their presence here does not imply they were run.

Start with these tasks

• Proxy OpenAI Responses API requests — Forward Responses API traffic through a Praxis AI listener to a compatible backend.
• Translate Responses API requests for a Chat Completions backend — Translate the Responses API shape for an OpenAI-compatible Chat Completions backend.
• Route inference requests by model — Use model identity to select the matching inference backend.
• Limit inference traffic by estimated token cost — Apply token-aware rate limiting to inference requests and reconcile reported usage.

Browse all configurations

• All configuration categories
• Anthropic
• Azure
• Bedrock
• Inference
• Openai
• Payload Processing
• Vertex