Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

1.5 KB
Raw Blame
apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  name: ruflo-ai-team
spec:
  template:
    metadata:
      annotations:
        autoscaling.knative.dev/maxScale: "20"
        run.googleapis.com/execution-environment: gen2
    spec:
      containerConcurrency: 40
      timeoutSeconds: 60
      serviceAccountName: ruflo-ai-team@PROJECT_ID.iam.gserviceaccount.com
      containers:
        - image: REGION-docker.pkg.dev/PROJECT_ID/ruflo/ruflo-ai-team:0.4.0
          ports: [{ containerPort: 8080 }]
          resources:
            limits: { cpu: "1", memory: 1Gi }
          env:
            - { name: RUFLO_AI_TEAM_PUBLIC_URL, value: "https://team.ruv.io" }
            - { name: RUFLO_AI_TEAM_STORE, value: "firestore" }
            - { name: RUFLO_AI_TEAM_OAUTH_ISSUER, value: "https://auth.cognitum.one" }
            - { name: RUFLO_AI_TEAM_OAUTH_AUDIENCE, value: "https://team.ruv.io/mcp" }
            # Semantic memory search. Without the key the service stays on the labelled
            # lexical fallback. The key needs the embeddings:run scope and belongs to the service.
            - name: RUFLO_AI_TEAM_EMBEDDINGS_KEY
              valueFrom: { secretKeyRef: { name: ruflo-ai-team-embeddings-key, key: latest, optional: true } }
            # Optional: RUFLO_AI_TEAM_ANON_RPM (default 600) caps unauthenticated requests per client per minute.
            # Optional: ALLOWED_ORIGINS replaces the browser CORS allowlist
            # (default: https://chatgpt.com,https://chat.openai.com,https://claude.ai).