Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
docs: update hermes (#15655)
Parth Sareen123b300af63b
diff --git a/docs/images/hermes.png b/docs/images/hermes.pngnew file mode 100644index 000000000..0b68d230eBinary files /dev/null and b/docs/images/hermes.png differdiff --git a/docs/integrations/hermes.mdx b/docs/integrations/hermes.mdxindex 3cabe4454..f2eee8271 100644--- a/docs/integrations/hermes.mdx+++ b/docs/integrations/hermes.mdx@@ -2,7 +2,9 @@title: Hermes Agent----Hermes Agent is a self-improving AI agent built by Nous Research. It features automatic skill creation, cross-session memory, and connects messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Email) to models through a unified gateway.+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.++## Quick start@@ -10,25 +12,56 @@ Hermes Agent is a self-improving AI agent built by Nous Research. It features auollama launch hermes```-### Pull a model+Ollama handles everything automatically:++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++<Note>Hermes on Windows requires WSL2. Install it with `wsl --install` and re-run from inside the WSL shell.</Note>++## Recommended models++**Cloud 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++**Local models:**++- `gemma4` — Reasoning and code generation locally (~16 GB VRAM)+- `qwen3.6` — Reasoning, coding, and visual understanding locally (~24 GB VRAM)++More models at [ollama.com/search](https://ollama.com/search?c=cloud).++## Connect messaging apps-Before running the setup wizard, make sure you have a model available. Hermes will auto-detect models downloaded through Ollama.+Link Telegram, Discord, Slack, WhatsApp, Signal, or Email to chat with your models from anywhere:```bash-ollama pull kimi-k2.5:cloud+hermes gateway setup```-See [Recommended models](#recommended-models) for more options.+## Reconfigure-### Install+Re-run the full setup wizard at any time:```bash-curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash+hermes setup```-### Set up+## Manual setup++If you'd rather drive Hermes's own wizard instead of `ollama launch hermes`, install it directly:++```bash+curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash+```-After installation, Hermes launches the setup wizard automatically. Choose **Quick setup**:+Hermes launches the setup wizard automatically. Choose **Quick setup**:```How would you like to set up Hermes?@@ -84,32 +117,3 @@ Connect a messaging platform? (Telegram, Discord, etc.)Launch hermes chat now? [Y/n]: Y```-## Recommended models--**Cloud models**:--- `kimi-k2.5:cloud` — Multimodal reasoning with subagents-- `qwen3.5:cloud` — Reasoning, coding, and agentic tool use with vision-- `glm-5.1:cloud` — Reasoning and code generation-- `minimax-m2.7:cloud` — Fast, efficient coding and real-world productivity--**Local models:**--- `gemma4` — Reasoning and code generation locally (~16 GB VRAM)-- `qwen3.5` — Reasoning, coding, and visual understanding locally (~11 GB VRAM)--More models at [ollama.com/search](https://ollama.com/models).--## Configure later--Re-run the setup wizard at any time:--```bash-hermes setup-```--To configure just messaging:--```bash-hermes setup gateway-```