LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
AppRisingofficial publisher

Hermes Agent (Nous Research)

App : A product you use directly

Self-hosted agent that learns from its tasks, creates its own skills, maintains persistent memory, and responds on Telegram, Discord, Slack, WhatsApp, or Signal.

The most serious alternative to OpenClaw, cleaner on privacy (MIT, zero telemetry), and able to import your OpenClaw config.

Official site GitHub · 256,856 ★ Docs
Overall score
9.1 /10
Security: nothing to flag
Utility
8.5
Reliability
10.0
Security
No caveat on record
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Most AI assistants forget everything between sessions and remain locked inside a single application. Hermes Agent addresses this by offering an autonomous agent that retains persistent memory, learns from each completed task, and can be reached from Telegram, Discord, Slack, WhatsApp, Signal or the terminal, without ever losing track of your projects.

In practice, the agent runs on your own machine, a five-dollar VPS, or serverless infrastructure such as Modal or Daytona. After each complex task, it automatically generates skills, meaning reusable procedures that it refines over time. Full-text search across conversation history lets it recall what it has already solved, and a user profile model deepens with every session.

Hermes Agent is aimed at users comfortable with a terminal who want an assistant capable of working in the background, scheduling recurring tasks in plain language, and delegating sub-tasks to parallel agents. It also suits developers who want to connect their own models or endpoints via OpenRouter, OpenAI, or their own infrastructure.

It is not suited to someone looking for a ready-to-use graphical interface with no configuration: installation goes through the terminal, setting up messaging integrations requires several steps, and the breadth of options may discourage non-technical users.

What it offers

  • ·Persistent memory across sessions: the agent retains your projects, preferences, and its problem-solving history.
  • ·Automatic skill creation and improvement: after each complex task, the agent generates a reusable procedure and refines it during subsequent use.
  • ·Natural-language task scheduling: a built-in scheduler runs reports, backups, and recurring briefings unattended.
  • ·Multi-platform messaging: a single instance responds on Telegram, Discord, Slack, WhatsApp, Signal, Email, and 20+ other surfaces from one gateway process.
  • ·Parallel sub-agents: the agent can delegate workstreams to isolated sub-agents running simultaneously.
  • ·Multi-provider compatibility: switch models at any time with hermes model without changing code, using Nous Portal, OpenRouter, OpenAI, or your own endpoint.
  • ·Web search, image generation, text-to-speech, and browser automation via Nous Portal (paid).
  • ·60+ built-in tools covering terminal, Docker, SSH, vision, and Python code execution via RPC.

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
macos, linux, windows, cli
Licence
MIT
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Local or cloud depending on use
Maintenance
Active
Last release
23 October 2026

Links and repository checked on 25 October 2026 · added on 15 February 2026

How to install Hermes Agent (Nous Research)

1. On macOS, Linux, or WSL2, run: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash 2. On Windows (native PowerShell), run: iex (irm https://hermes-agent.nousresearch.com/install.ps1), no admin rights required. 3. Reload your shell with source ~/.bashrc (or ~/.zshrc) so the hermes command becomes available. 4. Run hermes setup --portal to configure your model provider and tools via OAuth in a single step. 5. If your antivirus flags uv.exe on Windows, add %LOCALAPPDATA%\hermes\bin as an exception: this is a documented false positive. 6. Type hermes to start your first conversation.
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash

Official documentation ↗

In the same category

Whole category Autonomous assistants →