quickstart.md

Quickstart

Build the release binary:

make release

Start Praxis AI:

./target/release/praxis-ai

The server starts on 127.0.0.1:8080 with a built-in default configuration. Verify it:

curl http://127.0.0.1:8080/

{"status": "ok", "server": "praxis-ai"}

Route to an AI backend

Create praxis-ai.yaml:

listeners:
  - name: ai
    address: "127.0.0.1:8080"
    filter_chains: [openai]

filter_chains:
  - name: openai
    filters:
      - filter: openai_responses_format
      - filter: router
        routes:
          - path_prefix: "/v1"
            cluster: openai_backend
      - filter: headers
        request_set:
          - name: Host
            value: api.openai.com
      - filter: load_balancer
        clusters:
          - name: openai_backend
            endpoints:
              - "api.openai.com:443"
            tls:
              sni: "api.openai.com"

Start Praxis AI with your config:

./target/release/praxis-ai -c praxis-ai.yaml

Requests to port 8080 are now forwarded to the OpenAI API:

curl http://127.0.0.1:8080/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{"model": "gpt-4o", "input": "Hello"}'

Next steps

• Example configs: working YAML for supported features and integration patterns.
• Filters: AI filters and how to write your own.
• Praxis core: listener, filter-chain, routing, and load-balancer configuration.