upstream-archive/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-23 09:10:53 -05:00
Code Issues Packages Projects Releases Wiki Activity

update hermes docs

Browse Source
This commit is contained in:
Eva Ho
2026-06-25 12:25:20 -04:00
parent ada1eb5163
commit 38a4f5bffc
1 changed files with 138 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

173
docs/integrations/hermes.mdx
View File

@@ -2,116 +2,185 @@
title: Hermes Agent
---
Hermes Agent is a self-improving AI agent built by Nous Research. It features automatic skill creation, cross-session memory, and 70+ skills that it ships with by default.
[Hermes Agent](https://hermes-agent.nousresearch.com) is an assistant from Nous Research with memory, skills, subagents, tools, and messaging gateways.
![Hermes Agent with Ollama](/images/hermes.png)
## Get started
## Quick start
Launch Hermes with Ollama:
```bash
```shell
ollama launch hermes
```
Ollama handles everything automatically:
If Hermes is not installed, Ollama prompts to install it. Ollama configures the Ollama provider, sets your selected model as the default, and opens Hermes chat.
1. **Install** — If Hermes isn't installed, Ollama prompts to install it via the Nous Research install script
2. **Model** — Pick a model from the selector (local or cloud)
3. **Onboarding** — Ollama configures the Ollama provider, points Hermes at `http://127.0.0.1:11434/v1`, and sets your model as the primary
4. **Gateway** — Optionally connects a messaging platform (Telegram, Discord, Slack, WhatsApp, Signal, Email) and launches the Hermes chat
## Capabilities
## Recommended models
<div className="capability-list capability-list-full">
<div className="capability-list-grid">
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="comment" /></div>
<div>
<div className="capability-list-heading">Chat</div>
<div className="capability-list-copy">Ask questions about a repository or task</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="terminal" /></div>
<div>
<div className="capability-list-heading">Command line</div>
<div className="capability-list-copy">Run commands with Hermes</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="wrench" /></div>
<div>
<div className="capability-list-heading">Tool calling</div>
<div className="capability-list-copy">Use tools with compatible models</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="file-pen" /></div>
<div>
<div className="capability-list-heading">File edits</div>
<div className="capability-list-copy">Read and edit files in your project</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="users" /></div>
<div>
<div className="capability-list-heading">Subagents</div>
<div className="capability-list-copy">Split work across tasks</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="globe" /></div>
<div>
<div className="capability-list-heading">Web fetch</div>
<div className="capability-list-copy">Fetch and summarize web pages</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="image" /></div>
<div>
<div className="capability-list-heading">Vision</div>
<div className="capability-list-copy">Send images and screenshots</div>
</div>
</div>
<div className="capability-list-item">
<div className="capability-list-icon"><Icon icon="brain" /></div>
<div>
<div className="capability-list-heading">Thinking</div>
<div className="capability-list-copy">Use thinking controls with compatible models</div>
</div>
</div>
</div>
</div>
**Cloud models**:
## Models
- `kimi-k2.5:cloud` — Multimodal reasoning with subagents
- `glm-5.1:cloud` — Reasoning and code generation
- `qwen3.5:cloud` — Reasoning, coding, and agentic tool use with vision
- `minimax-m2.7:cloud` — Fast, efficient coding and real-world productivity
Choose a local or cloud model from Ollama when launching Hermes.
**Local models:**
<CardGroup cols={2}>
<Card title="Cloud models" icon="cloud" href="https://ollama.com/search?c=cloud">
Use larger models hosted by Ollama.
</Card>
<Card title="Local models" icon="cpu" href="https://ollama.com/search">
Run models on your own machine.
</Card>
</CardGroup>
- `gemma4` — Reasoning and code generation locally (~16 GB VRAM)
- `qwen3.6` — Reasoning, coding, and visual understanding locally (~24 GB VRAM)
Run Hermes with a model directly:
More models at [ollama.com/search](https://ollama.com/search?c=cloud).
```shell
ollama launch hermes --model gemma4:cloud
```
## Connect messaging apps
## Messaging apps
Link Telegram, Discord, Slack, WhatsApp, Signal, or Email to chat with your models from anywhere:
On first interactive launch, Ollama asks whether you want to connect a messaging app.
```bash
Connect one later with Hermes:
```shell
hermes gateway setup
```
## Reconfigure
Hermes supports Telegram, Discord, Slack, WhatsApp, Signal, Email, and more.
Re-run the full setup wizard at any time:
## Run without interaction
```bash
hermes setup
Use `--yes` with a model for scripts and repeatable setups:
```shell
ollama launch hermes --model gemma4:cloud --yes
```
## Manual setup
If you'd rather drive Hermes's own wizard instead of `ollama launch hermes`, install it directly:
<div className="manual-step-title">1. Install Hermes</div>
```bash
<CodeGroup>
```shell macOS / Linux
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```
```powershell Windows
irm https://hermes-agent.nousresearch.com/install.ps1 | iex
```
</CodeGroup>
<div className="manual-step-title">2. Choose Quick setup</div>
Hermes launches the setup wizard automatically. Choose **Quick setup**:
```
```text
How would you like to set up Hermes?
→ Quick setup — provider, model & messaging (recommended)
Full setup — configure everything
```
### Connect to Ollama
<div className="manual-step-title">3. Configure Ollama</div>
1. Select **More providers...**
2. Select **Custom endpoint (enter URL manually)**
3. Set the API base URL to the Ollama OpenAI-compatible endpoint:
- Select **More providers...**
- Select **Custom endpoint (enter URL manually)**
- Set the API base URL to the Ollama OpenAI-compatible endpoint:
```
```text
API base URL [e.g. https://api.example.com/v1]: http://127.0.0.1:11434/v1
```
4. Leave the API key blank (not required for local Ollama):
- Leave the API key blank. It is not required for local Ollama.
```
```text
API key [optional]:
```
5. Hermes auto-detects downloaded models, confirm the one you want:
- Confirm the model Hermes detects:
```
```text
Verified endpoint via http://127.0.0.1:11434/v1/models (1 model(s) visible)
Detected model: kimi-k2.5:cloud
Use this model? [Y/n]:
```
6. Leave context length blank to auto-detect:
- Leave context length blank to auto-detect:
```
```text
Context length in tokens [leave blank for auto-detect]:
```
### Connect messaging
<div className="manual-step-title">4. Connect messaging apps</div>
Optionally connect a messaging platform during setup:
```
Connect a messaging platform? (Telegram, Discord, etc.)
→ Set up messaging now (recommended)
Skip — set up later with 'hermes setup gateway'
```shell
hermes gateway setup
```
### Launch
<div className="manual-step-title">5. Launch Hermes</div>
```shell
hermes
```
Launch hermes chat now? [Y/n]: Y
```