Hermes Agent – Open-Source AI Agent with Persistent Memory
Hermes Agent is an open-source autonomous AI agent by Nous Research with persistent memory, automated skill creation, and multi-platform support. It runs on self-hosted servers, learns user preferences and projects, and interacts via Telegram, Discord, and more. It also offers batch processing, RL training, and trajectory export for MLOps and AI training.
Open Source · MIT License · By Nous Research
Hermes Agent
The AI agent that grows with you.
Install it on your server, give it your messaging accounts, and it becomes a persistent personal agent — learning your projects, building its own skills, and reaching you wherever you are. Not a chatbot. Not a copilot. An agent that lives on your machine and gets smarter every day.
Get Started Free Learn More
40+
Built-in Skills
5
Chat Platforms
MIT
License
100%
Self-Hosted
Everything You Need in One Agent
Hermes Agent combines persistent memory, automated skill creation, and multi-platform reach into a single open-source package.
Persistent Memory
Remembers your preferences, projects, and environment across every session. The longer it runs, the better it knows you — no re-explaining context every time.
Automated Skill Creation
When Hermes solves a hard problem, it writes a reusable skill document so it never forgets how. Skills are searchable, shareable, and compatible with the agentskills.io open standard.
Multi-Platform Gateway
Connect Telegram, Discord, Slack, WhatsApp, Signal, 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.
Scheduled Automations
Built-in cron scheduler with delivery to any platform. Set up daily reports, nightly backups, weekly audits, and morning briefings — all running unattended.
Parallel Sub-Agents
Spawn isolated sub-agents for parallel workstreams. Each gets its own conversation and terminal. Collapse multi-step pipelines into zero-context-cost turns via RPC.
Full Browser & Web Control
Web search, page extraction, full browser automation — navigate, click, type, screenshot. Plus vision analysis, image generation, text-to-speech, and multi-model reasoning.
Powerful Capabilities Out of the Box
From sandboxed code execution to real-time browser control — Hermes Agent handles it all.
Execution Environments
Local Terminal
Run commands directly on your machine
✓
Docker
Isolated container with security hardening
✓
SSH Remote
Execute on any remote server
✓
Modal / Singularity
Cloud and HPC execution backends
✓
LLM Providers
Nous Portal
Native OAuth integration
✓
OpenRouter
Access 200+ models via API key
✓
Custom API
Any OpenAI-compatible endpoint
✓
Local vLLM
Run models fully on-premise
✓
Skills System
Built-in Skills
MLOps, GitHub, diagramming, note-taking & more
40+
Auto-Created Skills
Agent writes new skills as it solves problems
∞
Community Hubs
Browse & install from agentskills.io with one command
✓
Open Standard
Portable SKILL.md format — create, share, reuse anywhere
✓
Security & Privacy
No Tracking
Zero telemetry, zero data collection
✓
Container Hardening
Read-only root, dropped capabilities, PID limits
✓
Local Data
All memory stored in ~/.hermes/ on your machine
✓
MIT License
Fully open source, audit every line of code
✓
What Is Hermes Agent?
Hermes Agent is an open-source autonomous AI agent built by Nous Research and released in February 2026. It's not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. Hermes lives on your server, remembers what it learns, and gets more capable the longer it runs. It supports Linux, macOS, and WSL2 — with no prerequisites, installing everything automatically via a single curl command.
Open source · MIT License · Built by Nous Research. All data stays on your machine. No telemetry, no tracking, no cloud lock-in.
Built for MLOps & AI Training
Beyond task automation — Hermes Agent is a platform for generating training data, running RL experiments, and exporting trajectories for fine-tuning.
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.
Get Started in Minutes
No prerequisites. Works on Linux, macOS & WSL2. Installs everything automatically.
1
Install
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
Interactive setup wizard
hermes setup
Or choose your model
hermes model
Connect to Nous Portal (OAuth), OpenRouter (API key), or your own endpoint. Interactive setup wizard.
3
Start Chatting
hermes
Full interactive CLI with tools, memory, and skills. That's it.
4
Go Multi-Platform (Optional)
Interactive gateway setup wizard
hermes gateway setup
Start the messaging gateway
hermes gateway
Install as a system service
hermes gateway install
Walk through connecting Telegram, Discord, Slack, or WhatsApp. Runs as a systemd service.
5
Keep It Up to Date
hermes update
Pulls the latest changes and reinstalls dependencies. Run anytime to get new features and fixes.
⚠️ Native Windows support is experimental. Please install WSL2 and run Hermes Agent from there.
Ready to Run Your Own Agent?
Self-hosted, open source, and free forever. One command to install, one command to start.
View on GitHub