Hermes Agent Launches Profile Builder, Configure AI Agent in 5 Steps
Nous Research has launched Profile Builder for Hermes Agent, integrating previously scattered command-line configurations into a one-stop visual web-based process. Users can complete agent role creation in 5 steps: setting identity name and description, selecting model and provider, configuring built-in skills, installing Skills Hub skills, connecting MCP servers, and finally previewing and confirming.
A self-evolving AI agent built by Nous Research. It is the only intelligent agent with a built-in learning loop—creating skills from experience, improving skills during use, actively persisting knowledge, searching past conversations, and gradually building a deep understanding of you across sessions. It can run on a $5 VPS, on a GPU cluster, or using nearly zero-cost Serverless infrastructure. It doesn't tie you to your laptop—you can chat with it on Telegram while it works on a cloud VM.
Supports any model—Nous Portal, OpenRouter (200+ models), NVIDIA NIM (Nemotron), Xiaomi MiMo, z.ai/GLM, Kimi/Moonshot, MiniMax, Hugging Face, OpenAI, or custom endpoints. Switch using hermes model—no code changes, no lock-in.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
Supports Linux, macOS, WSL2, and Android (Termux). The installer automatically handles platform-specific configurations.
Android / Termux: For tested manual installation paths, please refer to the Termux guide. On Termux, Hermes will install selected
.[termux] extensions, because the full .[all] extensions will pull voice dependencies incompatible with Android.
Windows: Run in PowerShell:
iex (irm https://hermes-agent.nousresearch.com/install.ps1)
After installation, you may need to restart the terminal, then run
hermes to start the conversation.
After installation:
source ~/.bashrc # Reload shell (or: source ~/.zshrc)
hermes # Start conversation! hermes # Interactive CLI — Start conversation
hermes model # Select LLM provider and model
hermes tools # Configure enabled tools
hermes config set # Set individual configuration items
hermes gateway # Start message gateway (Telegram, Discord, etc.)
hermes setup # Run full setup wizard (configure everything at once)
hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw)
hermes update # Update to the latest version
hermes doctor # Diagnose issues 📖 Full Documentation →
Hermes always allows you to use any provider, and this will not change. But if you don't want to apply for five different API Keys for models, web search, image generation, TTS, and cloud browser separately, Nous Portal covers everything with one subscription:
- 300+ models — Switch anytime with /model <name>
- Tool Gateway — Web search (Firecrawl), image generation (FAL), text-to-speech (OpenAI), cloud browser (Browser Use), all hosted via subscription. No need to register any additional accounts.
For a fresh installation, one command is enough:
hermes setup --portal
It will log in via OAuth, set Nous as the inference provider, and enable Tool Gateway. Use hermes portal info anytime to check routing status. See Tool Gateway documentation for full instructions.
You can switch back to your own API Key per tool at any time — the Gateway works at the tool granularity level, not all-or-nothing.
Hermes has two entry points: start the terminal UI with hermes, or run the gateway to chat with it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once in conversation, many slash commands work in both interfaces.
All documentation is located at hermes-agent.nousresearch.com/docs:
If you are coming from OpenClaw, Hermes can automatically import your settings, memory, skills, and API keys.
First installation: The installation wizard (hermes setup) will automatically detect ~/.openclaw and offer migration options before configuration begins.
Any time after installation:
hermes claw migrate # Interactive migration (full preset)
hermes claw migrate --dry-run # Preview what will be migrated
hermes claw migrate --preset user-data # Migrate only user data, without keys
hermes claw migrate --overwrite # Overwrite existing conflicting import content:
- SOUL.md — Personality file
- Memory — MEMORY.md and USER.md entries
- Skills — User-created skills → ~/.hermes/skills/openclaw-imports/
- Command whitelist — Approval mode
- Message settings — Platform configuration, allowed users, working directory
- API Keys — Keys in the whitelist (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)
- TTS assets — Workspace audio files
- Workspace instructions — AGENTS.md (using --workspace-target)
Use hermes claw migrate --help to see all options, or use the openclaw-migration skill for interactive agent-guided migration (including dry-run preview).
Contributions welcome! Please refer to the Contribution Guide for development setup, code style, and PR process.
Contributor Quick Start — Use the standard installer, then develop within the full git checkout it creates:
$HERMES_HOME/hermes-agent (usually ~/.hermes/hermes-agent). This matches
the layout used by hermes update, managed venv, lazy dependencies, gateway, and docs tooling.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
cd "${HERMES_HOME:-$HOME/.hermes}/hermes-agent"
uv pip install -e ".[all,dev]"
scripts/run_tests.sh
Manual Clone Alternative Path (for one-off clone / CI, or if you explicitly do not want to use the managed install layout):
curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv venv --python 3.11
source venv/bin/activate
python -m pytest tests/ -q
- 💬 Discord
- 📚 Skills Hub
- 🐛 Bug Reports
- 💡 Discussion
- 🔌 HermesClaw — Community WeChat Bridge: Run Hermes Agent and OpenClaw on the same WeChat account.
MIT — See LICENSE for details.
Built by Nous Research.
This page provides an editorial summary based on publicly available information. It is not a republished article. Use the source link below for the original report.