hermes 配置Ollama本地模型

躁动的青年

183人浏览 · 2026-07-16 19:08:04

躁动的青年 · 2026-07-16 19:08:04 发布

环境

Win11，WSL2，Ubuntu24.04

AI 提供商 WSL2 网络（Windows 用户）
AI 提供商 | Hermes Agent - Hermes 智能体

一、前置设置

Windows设置环境变量OLLAMA_HOST=0.0.0.0，开放 Ollama 局域网访问

wsl网络使用镜像模式的应该不用设置。

二、使用hermes model命令配置模型

hermes model

Select provider:
↑↓ navigate ENTER/SPACE select ESC cancel

   (○) Nous Portal (Everything your agent needs, 300+ models with bundled tool use)
   (○) OpenRouter (Pay-per-use API aggregator)
   (○) Mixture of Agents (named presets; aggregator acts after reference models)
   (○) NovitaAI (Cloud: Model API, Agent Sandbox, GPU Cloud)
   (○) LM Studio (Local desktop app with built-in model server)
   (○) Anthropic (Claude models via API key or Claude Code)
   (○) OpenAI ▸ (Codex CLI or direct OpenAI API)
→ (●) Qwen Cloud / DashScope (Qwen + multi-provider) ← currently active
   (○) xAI Grok ▸ (Direct API or SuperGrok / Premium+ OAuth)
   (○) Xiaomi MiMo (MiMo-V2.5 and V2 models: pro, omni, flash)
   (○) Tencent TokenHub (Hy3 Preview via tokenhub.tencentmaas.com)
   (○) NVIDIA NIM (Nemotron models via build.nvidia.com or local NIM)
   (○) GitHub Copilot ▸ (GitHub token API or copilot --acp process)
   (○) Hugging Face Inference Providers
   (○) Google AI Studio (Native Gemini API)
   (○) Google Vertex AI (Gemini via GCP; OAuth2 service account or ADC, GCP billing/quotas)
   (○) DeepSeek (V3, R1, coder, direct API)
   (○) Z.AI / GLM (Zhipu direct API)
   (○) Kimi / Moonshot ▸ (Coding Plan, Moonshot global & China endpoints)
   (○) StepFun Step Plan (Agent / coding models via Step Plan API)
   (○) MiniMax ▸ (Global, OAuth Coding Plan & China endpoints)
   (○) Ollama Cloud (Cloud-hosted open models, ollama.com)
   (○) Arcee AI (Trinity models, direct API)
   (○) GMI Cloud (Multi-model direct API)
   (○) Fireworks AI (OpenAI-compatible direct model API)
   (○) Kilo Code (Kilo Gateway API)
   (○) OpenCode ▸ (Zen pay-as-you-go or Go subscription)
   (○) AWS Bedrock (Claude, Nova, Llama, DeepSeek; IAM or API key)
   (○) Azure Foundry (OpenAI-style or Anthropic-style endpoint, your Azure AI deployment)
   (○) Qwen OAuth (Reuses local Qwen CLI login)
   (○) Alibaba Cloud Coding Plan (Dedicated coding tier)
   (○) custom (direct API)
   (○) DeepInfra — 100+ open models, pay-per-use
   (○) Upstage (Solar API)
   (○) Custom endpoint (enter URL manually)
   (○) Configure auxiliary models...
   (○) Leave unchanged

选择
→ (○) Custom endpoint (enter URL manually)

三、hermes model命令及后续选择

admin@UD26:~$ hermes model

Current model: qwen3.6-flash
Active provider: Qwen Cloud

Custom OpenAI-compatible endpoint configuration:

API base URL [e.g. https://api.example.com/v1]: http://localhost:11434/v1（填写Ollama服务地址）
API key [optional]:
Verified endpoint via http://localhost:11434/v1/models (8 model(s) visible)

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（选择2）
API mode: chat_completions
Available models:
1. gemma4:31b
2. gemma4:26b
3. qwen3.6:35b
4. qwen3.6:27b
5. qwen3.5:9b
6. deepseek-r1:1.5b
7. qwen3.5:35b
8. qwen3.5:27b
Select model [1-8] or type name: 3（选择模型）
Context length in tokens [leave blank for auto-detect]:（回车自动侦测（默认的简单），或填写对模型应值：262144，后续可再设置）
Display name [Local (localhost:11434)]:Ollama Local（可选改名，后续可再改）
Default model set to: qwen3.6:35b (via http://localhost:11434/v1)
💾 Saved to custom providers as "Ollama Local" (edit in config.yaml)

快速验证Ollama服务地址
在 WSL2 内部，测试是否可以连接到您的模型服务器
curl http://localhost:11434/v1/models

四、聊天测试hermes

输入命令hermes，聊天测试

五、显示配置信息hermes config show

admin@UD26:~$ hermes config show

┌─────────────────────────────────────────────────────────┐
│              ⚕ Hermes Configuration                    │
└─────────────────────────────────────────────────────────┘

◆ Paths
  Config:       /home/uadmin/.hermes/config.yaml
  Secrets:      /home/uadmin/.hermes/.env
  Install:      /home/uadmin/.hermes/hermes-agent

◆ API Keys
  OpenRouter     (not set)
  OpenAI (STT/TTS) (not set)
  Exa            (not set)
  Parallel       (not set)
  Firecrawl      (not set)
  Tavily         (not set)
  Browserbase    (not set)
  Browser Use    (not set)
  FAL            (not set)
  Anthropic      (not set)

◆ Model
  Model:        {'default': 'qwen3.6:35b', 'provider': 'custom', 'base_url': 'http://localhost:11434/v1', 'context_length': 262144, 'api_mode': 'chat_completions'}
  Max turns:    150

◆ Display
  Personality:  none
  Reasoning:    off
  Bell:         off
  User preview: first 2 line(s), last 2 line(s)

◆ Terminal
  Backend:      local
  Working dir:  .
  Timeout:      180s

◆ Timezone
  Timezone:     (server-local)

◆ Context Compression
  Enabled:      yes
  Threshold:    50%
  Target ratio: 20% of threshold preserved
  Protect last: 20 messages
  Protect first: 3 non-system head messages
  Model:        (auto)

◆ Messaging Platforms
  Telegram:     not configured
  Discord:      not configured

────────────────────────────────────────────────────────────
  hermes config edit     # Edit config file
  hermes config set <key> <value>
  hermes setup           # Run setup wizard

六、配置文件config.yaml

~/.hermes/config.yaml

七、修改配置文件hermes config edit

hermes config edit（修改的是~/.hermes/config.yaml文件）

设置模型上下文长度

hermes config set model.context_length 262144

八、再次使用hermes model命令查看

会多出一行

(●) Ollama Local (localhost:11434/v1) — qwen3.6:35b

Select provider:
  ↑↓ navigate  ENTER/SPACE select  ESC cancel

   (○) Nous Portal (Everything your agent needs, 300+ models with bundled tool use)
   (○) OpenRouter (Pay-per-use API aggregator)
   (○) Mixture of Agents (named presets; aggregator acts after reference models)
   (○) NovitaAI (Cloud: Model API, Agent Sandbox, GPU Cloud)
   (○) LM Studio (Local desktop app with built-in model server)
   (○) Anthropic (Claude models via API key or Claude Code)
   (○) OpenAI ▸ (Codex CLI or direct OpenAI API)
   (○) Qwen Cloud / DashScope (Qwen + multi-provider)
   (○) xAI Grok ▸ (Direct API or SuperGrok / Premium+ OAuth)
   (○) Xiaomi MiMo (MiMo-V2.5 and V2 models: pro, omni, flash)
   (○) Tencent TokenHub (Hy3 Preview via tokenhub.tencentmaas.com)
   (○) NVIDIA NIM (Nemotron models via build.nvidia.com or local NIM)
   (○) GitHub Copilot ▸ (GitHub token API or copilot --acp process)
   (○) Hugging Face Inference Providers
   (○) Google AI Studio (Native Gemini API)
   (○) Google Vertex AI (Gemini via GCP; OAuth2 service account or ADC, GCP billing/quotas)
   (○) DeepSeek (V3, R1, coder, direct API)
   (○) Z.AI / GLM (Zhipu direct API)
   (○) Kimi / Moonshot ▸ (Coding Plan, Moonshot global & China endpoints)
   (○) StepFun Step Plan (Agent / coding models via Step Plan API)
   (○) MiniMax ▸ (Global, OAuth Coding Plan & China endpoints)
   (○) Ollama Cloud (Cloud-hosted open models, ollama.com)
   (○) Arcee AI (Trinity models, direct API)
   (○) GMI Cloud (Multi-model direct API)
   (○) Fireworks AI (OpenAI-compatible direct model API)
   (○) Kilo Code (Kilo Gateway API)
   (○) OpenCode ▸ (Zen pay-as-you-go or Go subscription)
   (○) AWS Bedrock (Claude, Nova, Llama, DeepSeek; IAM or API key)
   (○) Azure Foundry (OpenAI-style or Anthropic-style endpoint, your Azure AI deployment)
   (○) Qwen OAuth (Reuses local Qwen CLI login)
   (○) Alibaba Cloud Coding Plan (Dedicated coding tier)
   (○) custom (direct API)
   (○) DeepInfra — 100+ open models, pay-per-use
   (○) Upstage (Solar API)
 → (●) Ollama Local (localhost:11434/v1) — qwen3.6:35b  ← currently active
   (○) Custom endpoint (enter URL manually)
   (○) Remove a saved custom provider
   (○) Configure auxiliary models...
   (○) Leave unchanged

九、通过命令行方式配置（未实践）

# 1. 设置模型提供商为自定义端点类型
hermes config set model.provider custom

# 2. 设置Ollama本地API地址（WSL2镜像网络直接用localhost即可）
hermes config set model.base_url http://localhost:11434/v1

# 3. 设置默认调用的模型名称
hermes config set model.default qwen3.6:35b

# 4. 设置API兼容模式为标准Chat Completions（匹配Ollama的OpenAI兼容接口）
hermes config set model.api_mode chat_completions

# 5. 固定上下文窗口长度为262144（256k）
hermes config set model.context_length 262144