Skip to Content
IntegrationHermes Agent

Using Ling in Hermes Agent

Hermes Agent  is a lightweight AI Agent framework that supports tool calling, multi-step planning, and OpenAI compatible LLM backends. By pointing the backend to Ant Ling, you can power Hermes Agent workflows with Ling — ideal for automation tasks, data processing, and more.

What You Need

Configuration

Run the following command to launch the interactive setup wizard:

hermes model

Follow the prompts to complete each step:

Select More providers... from the provider list
Select provider:

 →  Nous Portal (Nous Research subscription)
    OpenRouter (100+ models, pay-per-use)
    Anthropic (Claude models — API key or Claude Code)
    OpenAI Codex
    GitHub Copilot (uses GITHUB_TOKEN or gh auth token)
    Hugging Face Inference Providers (20+ open models)
    More providers...
    Cancel
Select Custom endpoint (enter URL manually) from the extended list
Select provider:

    GitHub Copilot ACP (spawns `copilot --acp --stdio`)
    Google AI Studio (Gemini models — OpenAI-compatible endpoint)
    Z.AI / GLM (Zhipu AI direct API)
    Kimi / Moonshot (Moonshot AI direct API)
    MiniMax (global direct API)
    MiniMax China (domestic direct API)
    Kilo Code (Kilo Gateway API)
    OpenCode Zen (35+ curated models, pay-as-you-go)
    OpenCode Go (open models, $10/month subscription)
    AI Gateway (Vercel — 200+ models, pay-per-use)
    Alibaba Cloud / DashScope Coding (Qwen + multi-provider)
 →  Custom endpoint (enter URL manually)
    Remove a saved custom provider
    Cancel
Enter https://api.ant-ling.com/v1 as the API Base URL
API base URL [e.g. https://api.example.com/v1]: https://api.ant-ling.com/v1
Go to the API Console  to create and enter your Ling API Key
API key [optional]: <YOUR_API_KEY>
Enter the model name — the example uses Ling-2.6-flash, change to Ling-2.6-1T, Ling-2.5-1T, or Ring-1T as needed
Model name (e.g. gpt-4, llama-3-70b): Ling-2.6-flash
Enter context length (leave blank for auto-detect) — setup is complete
Context length in tokens [leave blank for auto-detect]: 5000
Default model set to: Ling-2.6-flash (via https://api.ant-ling.com/v1)
  💾 Saved to custom providers as "api.ant-ling.com" (edit in config.yaml)

FAQ

AuthenticationError / 401 Error

  • Confirm both api_key and the OPENAI_API_KEY environment variable are set to your Ling API Key
  • Verify your API Key is active in the API Console 

Tool Call Response Format Incorrect

Ant Ling fully supports the OpenAI Function Calling specification. Check that the JSON Schema for your tool function parameters is valid.

Task Execution Timeout

For long-running generation tasks, enable stream=True to avoid timeouts. The synchronous call timeout is 90 seconds.

Was this page helpful?
Last updated on
Kilo CodeFAQ