diff --git a/projects/ai/project.yaml b/projects/ai/project.yaml
new file mode 100644
index 00000000..b3e982ac
--- /dev/null
+++ b/projects/ai/project.yaml
@@ -0,0 +1,18 @@
+config:
+  description: LocalAI & LLM Stuff
+
+apps:
+- name: localai
+  repoURL: https://go-skynet.github.io/helm-charts
+  chart: local-ai
+  targetRevision: 2.1.2
+
+- name: anythingllm
+  repo: bjw-s 
+  chart: app-template
+  targetRevision: 2.4.0
+
+- name: flowise
+  repo: bjw-s 
+  chart: app-template
+  targetRevision: 2.4.0
diff --git a/projects/ai/values/anythingllm.yml b/projects/ai/values/anythingllm.yml
new file mode 100644
index 00000000..170e29b9
--- /dev/null
+++ b/projects/ai/values/anythingllm.yml
@@ -0,0 +1,47 @@
+controllers:
+  main:
+    containers:
+      main:
+        image:
+          repository: mintplexlabs/anythingllm
+          tag: master
+
+env:
+  STORAGE_DIR: /data
+
+ingress:
+  main:
+    annotations:
+      cert-manager.io/cluster-issuer: vault-issuer
+    enabled: true
+    hosts:
+    - host: chat.dc
+      paths:
+      - path: /
+        service:
+          name: main
+          port: http
+    tls:
+    - hosts:
+      - chat.dc
+      secretName: anythingllm-tls
+
+persistence:
+  data:
+    accessMode: ReadWriteOnce
+    enabled: true
+    mountPath: /data
+    readOnly: false
+    size: 10Gi
+    type: persistentVolumeClaim
+
+securityContext:
+  privileged: false
+
+service:
+  main:
+    ports:
+      http:
+        enabled: true
+        port: 3001
+    type: ClusterIP
diff --git a/projects/ai/values/flowise.yml b/projects/ai/values/flowise.yml
new file mode 100644
index 00000000..854b56a0
--- /dev/null
+++ b/projects/ai/values/flowise.yml
@@ -0,0 +1,77 @@
+controllers:
+  main:
+    containers:
+      main:
+        image:
+          repository: flowiseai/flowise
+          tag: 1.4.7
+        command:
+          - flowise
+          - start
+
+env:
+  FLOWISE_USERNAME: nold
+  PORT: "3000"
+  DATABASE_PATH: /data/.flowise
+  APIKEY_PATH: /data/.flowise
+  SECRETKEY_PATH: /data/.flowise
+  LOG_PATH: /data/.flowise/logs
+
+  # NUMBER_OF_PROXIES= 1
+
+  # DATABASE_TYPE=postgres
+  # DATABASE_PORT=""
+  # DATABASE_HOST=""
+  # DATABASE_NAME="flowise"
+  # DATABASE_USER=""
+  # DATABASE_PASSWORD=""
+
+  # FLOWISE_USERNAME=user
+  # FLOWISE_PASSWORD=1234
+  # FLOWISE_SECRETKEY_OVERWRITE=myencryptionkey
+  # DEBUG=true
+  # LOG_LEVEL=debug (error | warn | info | verbose | debug)
+  # TOOL_FUNCTION_BUILTIN_DEP=crypto,fs
+  # TOOL_FUNCTION_EXTERNAL_DEP=moment,lodash
+
+  # LANGCHAIN_TRACING_V2=true
+  # LANGCHAIN_ENDPOINT=https://api.smith.langchain.com
+  # LANGCHAIN_API_KEY=your_api_key
+  # LANGCHAIN_PROJECT=your_project
+
+ingress:
+  main:
+    annotations:
+      cert-manager.io/cluster-issuer: vault-issuer
+    enabled: true
+    hosts:
+    - host: flowise.dc
+      paths:
+      - path: /
+        service:
+          name: main
+          port: http
+    tls:
+    - hosts:
+      - flowise.dc
+      secretName: flowise-tls
+
+persistence:
+  data:
+    accessMode: ReadWriteOnce
+    enabled: true
+    mountPath: /data
+    readOnly: false
+    size: 10Gi
+    type: persistentVolumeClaim
+
+securityContext:
+  privileged: false
+
+service:
+  main:
+    ports:
+      http:
+        enabled: true
+        port: 3000
+    type: ClusterIP
diff --git a/projects/ai/values/localai.yaml b/projects/ai/values/localai.yaml
new file mode 100644
index 00000000..9753a876
--- /dev/null
+++ b/projects/ai/values/localai.yaml
@@ -0,0 +1,68 @@
+replicaCount: 1
+
+deployment:
+  image: quay.io/go-skynet/local-ai:master
+  env:
+    THREADS: 16
+    CONTEXT_SIZE: 512
+    DEBUG: "true"
+  modelsPath: "/models"
+  download_model:
+    # To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox
+    image: busybox
+  prompt_templates:
+    # To use cloud provided (eg AWS) image, provide it like: 1234356789.dkr.ecr.us-REGION-X.amazonaws.com/busybox
+    image: busybox
+  pullPolicy: Always
+  imagePullSecrets: []
+    # - name: secret-names
+
+# Prompt templates to include
+# Note: the keys of this map will be the names of the prompt template files
+promptTemplates:
+  {}
+  # ggml-gpt4all-j.tmpl: |
+  #   The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
+  #   ### Prompt:
+  #   {{.Input}}
+  #   ### Response:
+
+# Models to download at runtime
+models:
+  # Whether to force download models even if they already exist
+  forceDownload: false
+
+  # The list of URLs to download models from
+  # Note: the name of the file will be the name of the loaded model
+  list:
+    - url: "https://gpt4all.io/models/ggml-gpt4all-j.bin"
+      # basicAuth: base64EncodedCredentials
+
+  persistence:
+    pvc:
+      enabled: true
+      size: 6Gi
+      accessModes:
+        - ReadWriteOnce
+
+service:
+  type: ClusterIP
+  port: 80
+
+ingress:
+  enabled: true
+  className: "ingress-internal"
+  annotations:
+    cert-manager.io/cluster-issuer: vault-issuer
+  hosts:
+    - host: ai.dc
+      paths:
+        - path: /
+          pathType: ImplementationSpecific
+  tls: 
+    - secretName: localai-tls
+      hosts:
+        - ai.dc
+
+image:
+  pullPolicy: IfNotPresent
diff --git a/projects/localai/values/localai.yaml b/projects/localai/values/localai.yaml
deleted file mode 100644
index 421d2ca8..00000000
--- a/projects/localai/values/localai.yaml
+++ /dev/null
@@ -1,130 +0,0 @@
-image:
-  ## @param image.registry Image registry
-  registry: quay.io
-
-  ## @param image.repository Image repository
-  repository: go-skynet/local-ai
-
-  ## @param image.tag Image tag
-  tag: v2.2.0-ffmpeg
-
-  ## @param image.digest Image digest
-  digest: ""
-
-  ## @param image.pullPolicy Image pull policy
-  pullPolicy: IfNotPresent
-
-podSecurityContext:
-  fsGroup: 2000
-
-## @param securityContext Container security context
-securityContext:
-  capabilities:
-    drop:
-    - ALL
-  #readOnlyRootFilesystem: true
-  runAsNonRoot: true
-  runAsUser: 1000
-
-ingress:
-  ## @param ingress.enabled Enable ingress controller resource
-  enabled: true
-
-  ## @param ingress.ingressClassName IngressClass that will be be used to implement the Ingress
-  ingressClassName: "ingress-internal"
-
-  ## @param ingress.pathType Ingress path type
-  pathType: ImplementationSpecific
-
-  ## @param ingress.annotations Ingress annotations
-  annotations:
-    cert-manager.io/cluster-issuer: vault-issuer
-    traefik.ingress.kubernetes.io/router.tls: 'true'
-
-    # kubernetes.io/ingress.class: nginx
-    # kubernetes.io/tls-acme: "true"
-
-  ## @param ingress.hosts[0].host Hostname to your LocalAI installation
-  ## @param ingress.hosts[0].paths Paths within the url structure
-  hosts:
-    - host: ai.dc
-      paths:
-        - /
-
-  ## @param ingress.tls TLS configuration
-  tls:
-    - secretName: local-ai-tls
-      hosts:
-        - ai.dc
-
-## @param resources CPU/Memory resource requests/limits
-resources: {}
-  # limits:
-  #   cpu: 100m
-  #   memory: 128Mi
-  # requests:
-  #   cpu: 100m
-  #   memory: 128Mi
-
-## @param extraArgs Additional container arguments
-extraArgs: {}
-  # name: ""
-
-## @param extraEnvVars Additional container environment variables
-extraEnvVars: []
-  # - name: MY-NAME
-  #   value: "MY-VALUE"
-
-## @param extraEnvVarsCM Name of existing ConfigMap containing additional container environment variables
-extraEnvVarsCM:
-
-## @param extraEnvVarsSecret Name of existing Secret containing additional container environment variables
-extraEnvVarsSecret:
-
-init:
-  ## @param init.securityContext Init security context
-  securityContext:
-    capabilities:
-      drop:
-      - ALL
-  # readOnlyRootFilesystem: true
-    runAsNonRoot: true
-    runAsUser: 1000
-
-  ## @param init.resources Init CPU/Memory resource requests/limits
-  resources: {}
-    # limits:
-    #   cpu: 100m
-    #   memory: 128Mi
-    # requests:
-    #   cpu: 100m
-    #   memory: 128Mi
-
-persistence:
-  ## @param persistence.enabled Enable persistence using PVC
-  enabled: true
-  accessMode: ReadWriteOnce
-  size: 1Gi
-  storageClass: ssd
-
-config:
-  ## @param config.galleries Model galleries
-  galleries:
-    - name: model-gallery
-      url: github:go-skynet/model-gallery/index.yaml
-
-  ## @param config.preloadModels Models to preload (configure liveness probe initial delay according to model download time)
-  preloadModels:
-    - id: model-gallery@text-embedding-ada-002
-    - url: github:go-skynet/model-gallery/gpt4all-j.yaml
-      name: gpt-3.5-turbo
-    - id: model-gallery@stablediffusion
-    - id: model-gallery@whisper-1
-    - id: model-gallery@voice-en-us-kathleen-low
-
-# FIXME:due to timeout during download
-readinessProbe:
-  enabled: false
-
-livenessProbe:
-  enabled: false