diff --git a/.github/workflows/docker-image.yml b/.github/workflows/docker-image.yml
index fa1c04e..fb443c8 100644
--- a/.github/workflows/docker-image.yml
+++ b/.github/workflows/docker-image.yml
@@ -9,7 +9,7 @@ permissions:
   contents: read
 
 env:
-  IMAGE_NAME: mlogclub/cs-ai-agent
+  IMAGE_NAME: mlogclub/agent-desk
 
 jobs:
   build:
diff --git a/README.md b/README.md
index b3a6e22..d5c9755 100644
--- a/README.md
+++ b/README.md
@@ -270,11 +270,11 @@ flowchart LR
 If you only need to build the application image, prepare MySQL and Qdrant yourself and mount a configuration file:
 
 ```bash
-docker build -t cs-ai-agent .
+docker build -t mlogclub/agent-desk .
 docker run --rm -p 8083:8083 \
   -v $(pwd)/docker/cs-ai-agent.yaml:/app/config/config.yaml:ro \
   -v cs-ai-agent-data:/app/data \
-  cs-ai-agent
+  mlogclub/agent-desk
 ```
 
 Compose uses [docker/cs-ai-agent.yaml](docker/cs-ai-agent.yaml) as the in-container configuration. The application reaches `mysql` and `qdrant` through Docker service names.
diff --git a/README_ZH.md b/README_ZH.md
index e772ecb..4765494 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -270,11 +270,11 @@ flowchart LR
 如果只需要构建应用镜像，可以自行准备 MySQL 和 Qdrant，并挂载配置文件：
 
 ```bash
-docker build -t cs-ai-agent .
+docker build -t mlogclub/agent-desk .
 docker run --rm -p 8083:8083 \
   -v $(pwd)/docker/cs-ai-agent.yaml:/app/config/config.yaml:ro \
   -v cs-ai-agent-data:/app/data \
-  cs-ai-agent
+  mlogclub/agent-desk
 ```
 
 Compose 使用 [docker/cs-ai-agent.yaml](docker/cs-ai-agent.yaml) 作为容器内配置，应用会通过 Docker 内部服务名访问 `mysql` 和 `qdrant`。
diff --git a/docker-compose.yml b/docker-compose.yml
index ebce5a3..621737c 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -32,7 +32,7 @@ services:
     build:
       context: .
       dockerfile: Dockerfile
-    image: cs-ai-agent:latest
+    image: mlogclub/agent-desk:latest
     restart: unless-stopped
     depends_on:
       mysql: