Open Source · MIT License

The agent that
grows with you.

Install it on a machine, give it your messaging accounts, and it becomes a persistent personal agent that grows with you — learning your projects, building its own skills, and reaching you wherever you are.

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Works on Linux & macOS · No Python prerequisite · Installs everything automatically

Not a coding copilot tethered to an IDE. Not a chatbot wrapper around a single API. An autonomous agent that lives on your server, remembers what it learns, and gets more capable the longer it runs.

What it does

💬

Lives Where You Do

Telegram, Discord, Slack, WhatsApp, and CLI — all from a single gateway process. Voice memo transcription, cross-platform continuation. Start a conversation on Telegram, pick it up in your terminal.

🧠

Grows the Longer It Runs

Persistent memory across sessions — it learns your preferences, projects, and environment. When it solves a hard problem, it writes a skill document so it never forgets how. Skills are searchable and shareable.

Scheduled Automations

Built-in cron scheduler with delivery to any platform. Natural language scheduling for daily reports, nightly backups, weekly audits, morning briefings — all running unattended through the gateway.

🔀

Delegates & Parallelizes

Spawn isolated subagents for parallel workstreams. Each gets its own conversation and terminal. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.

🔒

Real Sandboxing

Five terminal backends: local, Docker, SSH, Singularity, and Modal. Container security hardening with read-only root, dropped capabilities, PID limits, and namespace isolation.

🌐

Full Web & Browser Control

Web search, page extraction, full browser automation — navigate, click, type, screenshot. Plus vision analysis, image generation, text-to-speech, and multi-model collaborative reasoning.

See it in action

hermes

40+ built-in tools

🔍 Web Search
💻 Terminal
📁 File System
🌐 Browser
👁 Vision
🎨 Image Gen
🔊 Text-to-Speech
🧠 Memory
📋 Task Planning
Cron Jobs
🐍 Code Execution
🔀 Subagents
📚 Skills
🤖 Multi-Model Reasoning
📨 Messaging
🔎 Session Search

Works with everything

Chat Platforms

Telegram Discord Slack WhatsApp CLI

LLM Providers

Nous Portal OpenRouter Custom API

Execution Environments

Local Docker SSH Singularity Modal

40+ built-in skills & growing

Skills are procedural memory — reusable approaches for recurring tasks. The agent creates them when it solves hard problems, and loads them automatically when similar tasks come up. Install more from community hubs with a single command.

Built-in Skills

40+ skills bundled out of the box covering MLOps, GitHub workflows, diagramming, note-taking, and more. The agent also creates new skills on the fly as it works.

Skills Hub Integrations

agentskills.io GitHub Repos ClawHub LobeHub Claude Code Marketplace

Browse, install, and manage skills from multiple community hubs. Quarantine and audit systems keep your agent safe.

Open Standard

Skills follow the agentskills.io open format — portable SKILL.md files that any agent can use. Create your own and share them.

Get started in 60 seconds

1

Install

bash
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Installs uv, Python 3.11, clones the repo, sets up everything. No sudo needed.

2

Configure

bash
# Interactive setup wizard
hermes setup

# Or choose your model
hermes model

Connect to Nous Portal (OAuth), OpenRouter (API key), or your own endpoint.

3

Start chatting

bash
hermes

That's it. Full interactive CLI with tools, memory, and skills.

4

Go multi-platform (optional)

bash
# Start the messaging gateway
hermes gateway

# Install as a system service
hermes gateway install

Connect Telegram, Discord, Slack, or WhatsApp. Runs as a systemd service.

Windows? Use WSL or PowerShell:

powershell
irm https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.ps1 | iex

Research-ready

Batch Processing

Generate thousands of tool-calling trajectories in parallel with automatic checkpointing. Configurable workers, batch sizes, and toolset distributions.

RL Training

Atropos integration for reinforcement learning on agent behaviors. 11 tool-call parsers for training any model architecture.

Trajectory Export

Export conversations in ShareGPT format for fine-tuning. Trajectory compression fits training data into token budgets.

ARTIFICIAL INTELLIGENCE MADE HUMAN

NODES

THE AI ACCELERATOR COMPANY

NODES