qwen-code Docker & Self-Hosted Deployment

GitHub

An open-source AI coding agent that lives in your terminal.

28,650 stars TypeScript TypeScript 90 files · ~469,070 tokens #agentic#ai#ai-agent#ai-coding#cli#coding-agent#developer-tools#llm
RAW Compose
1. Pull Image (DOCKERHUB) docker pull library/${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}
2. Docker Run (1-Click Launch) docker run -d --name qwen-code --restart always ${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}
3. Podman Run podman run -d --name qwen-code --restart always ${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/library/${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}:latest
5. ORAS Pull (OCI Artifact) oras pull ${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}
6. Compose Deployment docker compose up -d
integration-tests/terminal-bench/ci-tasks/hello-world/docker-compose.yaml
Download .yml 
services:
  client:
    build:
      dockerfile: Dockerfile
    image: ${T_BENCH_TASK_DOCKER_CLIENT_IMAGE_NAME}
    container_name: ${T_BENCH_TASK_DOCKER_CLIENT_CONTAINER_NAME}
    command: ['sh', '-c', 'sleep infinity']
    environment:
      - TEST_DIR=${T_BENCH_TEST_DIR}
    volumes:
      - ${T_BENCH_TASK_LOGS_PATH}:${T_BENCH_CONTAINER_LOGS_PATH}
      - ${T_BENCH_TASK_AGENT_LOGS_PATH}:${T_BENCH_CONTAINER_AGENT_LOGS_PATH}