hermes

#进入hermes源码
./setup-hermes.sh
source ~/.bashrc

hermes model
tools #开启工具
gateway setup
gateway start #启动gateway
config set
setup #重新执行向导模式

$ hermes model
Custom OpenAI-compatible endpoint configuration:

API base URL [e.g. https://api.example.com/v1]: http://150.158.34.129:8080/v1
API key [optional]: *******************************************************************
                                                                                       Warning: could not verify this endpoint via http://150.158.34.129:8080/v1/models. Hermes will still save it.
  If /v1 should not be in the base URL, try: http://150.158.34.129:8080

Select API compatibility mode:
  1. Auto-detect [current]
     Use Hermes URL heuristics; best for standard OpenAI-compatible endpoints.
  2. Chat Completions
     Use /chat/completions for standard OpenAI-compatible servers.
  3. Responses / Codex
     Use /responses for Codex-compatible tool-calling backends.
  4. Anthropic Messages
     Use /v1/messages for Anthropic-compatible endpoints.
Choice [1-4, Enter to keep current/detected]: 2
  API mode: chat_completions
Model name (e.g. gpt-4, llama-3-70b): minimax-m2.5
Context length in tokens [leave blank for auto-detect]:
Display name [150.158.34.129:8080]: minimax-m2.5
Default model set to: minimax-m2.5 (via http://150.158.34.129:8080/v1)
  💾 Saved to custom providers as "minimax-m2.5" (edit in config.yaml)

hermes profile create sunwukong

sunwukong setup

hermes profile list

kill -9 $(lsof -t -i :8080)

hermes ​

hermes