DeepSeek Harness
DeepSeek // Web UI, desktop app
An early preview; interfaces and configuration may change between versions.
Install
npx @deepseek-ai/dsh web01 Installation reference
Official installation commands and links for compatible third-party tools. DAYWORLD does not host downloads, and tool names do not imply partnership.
[ A ]From model makers6
DeepSeek // Web UI, desktop app
An early preview; interfaces and configuration may change between versions.
Install
npx @deepseek-ai/dsh webOpenAI // Terminal, IDE, app
Install
npm install -g @openai/codexxAI // Terminal
Install
curl -fsSL https://x.ai/cli/install.sh | bashAnthropic // Terminal, IDE, desktop, web
Install
curl -fsSL https://claude.ai/install.sh | bashMoonshot AI // Terminal, desktop, IDE
Install
curl -fsSL https://code.kimi.com/kimi-code/install.sh | bashGoogle // Terminal
Install
npm install -g @google/gemini-cli[ B ]Open-source agents2
Open source // Terminal, desktop, IDE
Install
curl -fsSL https://opencode.ai/v2/install | bashOpen source // Terminal
Install
curl -fsSL https://pi.dev/install.sh | sh[ C ]Agent platforms3
Nous Research // Terminal
Install
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bashOpen source // Your machine, as a background service
Install
curl -fsSL https://openclaw.ai/install.sh | bashOpen source // Messaging apps, web dashboard
Install
uv tool install astrbot02 Connection settings
Once your service is provisioned, prepare your assigned endpoint, API key, and model ID; this public site has no account backend.
Step one
Confirm your assigned endpoint, API key, and permitted model IDs from your service plan.
Step two
Enter the settings in the configuration file or environment variables, then make a test request.
03 Tool setup
Choose a tool for configuration examples. Confirm your provisioned endpoint, API key, and supported protocol first.
Third-party tool configuration reference.
AFrom model makersBOpen-source agentsCAgent platforms
DeepSeek
# Developer preview: starts the web UI
npx @deepseek-ai/dsh web
# Then open http://127.0.0.1:3080
OpenAI
model = "<model-id>"
model_provider = "dayworld"
[model_providers.dayworld]
name = "DAYWORLD"
base_url = "https://api.worldnite.cn/v1"
env_key = "DAYWORLD_API_KEY"
wire_api = "responses"
xAI
# Windows PowerShell: irm https://x.ai/cli/install.ps1 | iex
cd your-project
grok
Anthropic
{
"env": {
"ANTHROPIC_BASE_URL": "https://api.worldnite.cn",
"ANTHROPIC_AUTH_TOKEN": "<DAYWORLD_API_KEY>",
"ANTHROPIC_MODEL": "<model-id>"
}
}
Moonshot AI
kimi
/login
# Choose Kimi Code sign-in or an Open Platform API key
export GEMINI_API_KEY="<DAYWORLD_API_KEY>"
export GOOGLE_GEMINI_BASE_URL="https://api.worldnite.cn"
export GEMINI_MODEL="<model-id>"
geminiOpen source
{
"providers": {
"dayworld": {
"name": "DAYWORLD",
"env": ["DAYWORLD_API_KEY"],
"package": "@opencode/ai/providers/openai-compatible",
"settings": { "baseURL": "https://api.worldnite.cn/v1" },
"models": { "<model-id>": { "name": "<model name>" } }
}
}
}
Open source
pi
/login # sign in to a provider
/model # pick an available model
Nous Research
hermes model
# Choose "Custom endpoint", then enter:
# API base URL https://api.worldnite.cn/v1
# API key <DAYWORLD_API_KEY>
# Model name <model-id>
Open source
openclaw onboard --install-daemon
# Choose "Custom provider", then enter
# https://api.worldnite.cn/v1 and <model-id>
Open source
astrbot
# Open the web dashboard and add a model provider
# with the values from your console
04 Security
Install tools only from their official website or repository.
Use environment variables or a secret manager. Do not hard-code keys or share them in group chats.
Use separate development, testing, and production keys to limit the impact of rotation or revocation.
Review and test generated code patches and configuration changes before merging or deploying.