# Hermes-Agent vs Runner H

Hermes-Agent records 3,638,741 monthly visits with -5.4% month-over-month growth and Freemium pricing. Runner H records 45,054 monthly visits with -32.6% growth and Freemium, Paid, Contact for Pricing pricing.

| Metric | [Hermes-Agent](https://openaitools.app/tool/hermes-agent-1) | [Runner H](https://openaitools.app/tool/runner-h) |
| :--- | :--- | :--- |
| Website URL | https://hermes-agent.nousresearch.com | https://www.hcompany.ai |
| Categories | AI Agent, AI Assistant, AI Developer Tools, Open Source AI Models | AI Agent, AI API, Large Language Models (LLMs) |
| Pricing Model | Freemium | Freemium, Paid, Contact for Pricing |
| Monthly Visits | 3,638,741 | 45,054 |
| MoM Growth Rate | -5.4% | -32.6% |
| Primary Market | United States | France |
| Direct Visits | 1,053,593 | 21,414 |
| Review Score | 4.6 | 4.2 |
| Saved Count | 1 | 0 |
| Supported Platforms | Website | Website |

## Hermes-Agent

Hermes-Agent is the officially published agent from Nous Research, distributed free and open source under the MIT license. Rather than a single chat window, it is designed as a long-lived assistant that persists conversations, memories, and self-authored skills between sessions, so solved problems become reusable capabilities instead of one-off prompts. The desktop app and install script support macOS 12+, Windows 10/11, and most Linux distributions.

Its reach is deliberately broad. One agent and one shared memory can connect to Telegram, Discord, Slack, WhatsApp, Signal, email, and the command line, so the same assistant follows you across surfaces. Beyond conversation it can browse and automate the web, use vision, generate images and speech, and reason across multiple models, while isolated subagents handle delegated work with their own terminals and Python RPC scripts to keep the main context light.

Automation and safety are first-class: natural-language scheduling runs recurring reports, backups, and briefings unattended through the gateway, and sandboxing is available across five backends including local, Docker, SSH, Singularity, and Modal with container hardening and namespace isolation. The core agent is free; model providers and optional hosted services are billed separately, and Nous Portal offers usage-based cloud agents in addition to free and low-cost tiers.

**Pricing & Plans:** The Hermes-Agent software is free and open source under the MIT license; model providers and optional hosted services are billed separately. Nous Portal offers a free pay-as-you-go tier plus Plus, Super, and Ultra cloud plans with usage, hosted tools, and cloud hosting, so you can bring your own keys or pay for managed credits.

- **Persistent memory and self-written skills:** Hermes keeps conversations, memories, and skills between sessions, and turns solutions it has already found into reusable capabilities you can call again.
- **Every surface in one agent:** Connect Telegram, Discord, Slack, WhatsApp, Signal, email, and the CLI to a single agent with one shared memory, so context follows you across platforms.
- **Natural-language scheduling:** Describe recurring reports, backups, or daily briefings in plain language and let them run unattended through the gateway.
- **Subagent delegation:** Spawn isolated subagents with their own conversations, terminals, and Python RPC scripts to run zero-context-cost pipelines in parallel.
- **Flexible sandbox backends:** Run untrusted work in local, Docker, SSH, Singularity, or Modal environments with container hardening and namespace isolation.

**Strengths:** Genuinely free and MIT-licensed, with no mandatory subscription to use the core agent; Persistent memory and auto-generated skills make it compound in usefulness over time; Unusually wide platform reach for a single agent, from Telegram to the command line; Multiple sandbox backends and subagent isolation suit serious automation work

**Limitations:** Self-hosting and provider setup demand real technical comfort compared with hosted chat apps; You bring your own model provider keys or pay for Nous Portal credits, so costs vary; Cloud hosting capacity per tier is modest, which can limit heavy always-on workloads

[Profile (Markdown)](https://openaitools.app/tool/hermes-agent-1.md)

## Runner H

Runner H is H Company's agentic platform for automating real work on real systems. The core premise is computer use: instead of stitching together API integrations, the agents interact with software the way a person does, clicking, typing, scrolling and reading screens. That makes it applicable to the large share of enterprise tooling that has no usable API, including desktop applications and internal portals.

The product is delivered three ways. Enterprise customers get forward-deployed engineers who learn their systems and build custom agents on existing infrastructure, backed by SOC 2 Type II, ISO 27001 and GDPR compliance. Builders can use the Agents API, which runs an agent in a cloud-hosted browser or on a desktop with an API, SDK, MCP connector and CLI, plus per-session concurrency limits. Researchers and developers can call the Models API, an OpenAI-compatible endpoint for H Company's multimodal Holo4 models, which are also published as open weights on Hugging Face.

The research underneath is measured on OSWorld, a benchmark for computer-use agents, where H Company reports Holo4 27B at 85.2% and Holo4 35B-A3B at 80.8%. A free Chrome extension, HoloTab, is the quickest way to see the agents in action on everyday browser tasks, and the same models power document OCR and element localization for developers.

**Pricing & Plans:** Freemium with usage-based tiers. The Agents API has a free tier (about 3 concurrent agents, roughly 60 sessions per month), then Builder at $20/month (about 10 concurrent agents, roughly 1,000 sessions) and Startup at $200/month (about 100 concurrent agents, roughly 10,000 sessions), with top-ups billed at model cost plus 20%. Enterprise pricing is custom. The Models API is token-based, and HoloTab, HoloDesktop CLI and open weights are free ways to try the technology.

- **No-integration computer use:** Agents operate browsers, desktop applications and internal systems by clicking, typing and reading the screen, so tools without APIs can still be automated.
- **Three ways to deploy:** Choose on-site enterprise deployment with forward-deployed engineers, the Agents API for builders, or the OpenAI-compatible Models API for custom agent loops.
- **Holo4 multimodal models:** Text, image and document input with computer-use ability, available via API, as self-hosted open weights, and with zero data retention options.
- **HoloTab Chrome extension:** A free browser companion and the fastest way to experience computer-use agents on tasks like summarising pages, drafting replies or preparing for meetings.
- **Enterprise security and compliance:** SOC 2 Type II, ISO 27001 and GDPR alignment, datacenter or residential proxy options, and enterprise controls such as SSO and workflow orchestration.

**Strengths:** Works on existing software without integrations or system rebuilds; Flexible access via enterprise deployment, Agents API or Models API; Open-weight Holo4 models and an OpenAI-compatible endpoint reduce lock-in; Strong enterprise compliance posture with SOC 2 Type II, ISO 27001 and GDPR

**Limitations:** Enterprise deployment requires a sales conversation rather than self-serve signup; Session allowances and concurrency are capped on lower tiers and top-ups carry a 20% margin; Computer-use agents still need supervision on complex or high-stakes workflows

[Profile (Markdown)](https://openaitools.app/tool/runner-h.md)

## Frequently Asked Questions

### How do Hermes-Agent and Runner H compare in monthly traffic?

Hermes-Agent has 3,638,741 monthly visits, while Runner H has 45,054. Traffic estimates describe audience size, not product quality.

### How do their growth rates compare?

Hermes-Agent has a month-over-month growth rate of -5.4%; Runner H has -32.6%.

### How does pricing compare?

Hermes-Agent: Freemium. The Hermes-Agent software is free and open source under the MIT license; model providers and optional hosted services are billed separately. Nous Portal offers a free pay-as-you-go tier plus Plus, Super, and Ultra cloud plans with usage, hosted tools, and cloud hosting, so you can bring your own keys or pay for managed credits. Runner H: Freemium, Paid, Contact for Pricing. Freemium with usage-based tiers. The Agents API has a free tier (about 3 concurrent agents, roughly 60 sessions per month), then Builder at $20/month (about 10 concurrent agents, roughly 1,000 sessions) and Startup at $200/month (about 100 concurrent agents, roughly 10,000 sessions), with top-ups billed at model cost plus 20%. Enterprise pricing is custom. The Models API is token-based, and HoloTab, HoloDesktop CLI and open weights are free ways to try the technology.

## Alternatives

| # | Tool Name | Monthly Visits | MoM Growth Rate | Pricing Model | Summary | Profile (Markdown) |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | [DeepSeek](https://openaitools.app/tool/deepseek) | 372,761,591 | +4.3% | Freemium | High-efficiency open-weight and hosted reasoning AI powered by DeepSeek-V4 and R1 at ultra-low token costs. | [.md](https://openaitools.app/tool/deepseek.md) |
| 2 | [Manus](https://openaitools.app/tool/manus) | 19,195,779 | -1.7% | Free Trial | A general-purpose AI agent that executes tasks, not just answers them | [.md](https://openaitools.app/tool/manus.md) |
| 3 | [Replit](https://openaitools.app/tool/replit) | 10,016,437 | -7.7% | Freemium, Paid | Describe your idea and Replit builds a working app in minutes | [.md](https://openaitools.app/tool/replit.md) |
| 4 | [n8n](https://openaitools.app/tool/n8n) | 4,522,449 | -7.4% | Freemium | Open-source workflow automation built for AI agents and technical teams | [.md](https://openaitools.app/tool/n8n.md) |
| 5 | [Apify](https://openaitools.app/tool/apify) | 4,147,762 | +3.9% | Freemium, Contact for Pricing | Run thousands of ready-made web scrapers and AI agents from one cloud platform | [.md](https://openaitools.app/tool/apify.md) |
| 6 | [Clawdbot (OpenClaw)](https://openaitools.app/tool/clawdbot) | 1,903,068 | -25.4% | Paid, Free | Similar local-first design and chat app connectivity, but lacks Hermes' specific multi-platform messaging framework. | [.md](https://openaitools.app/tool/clawdbot.md) |
| 7 | [MindStudio](https://openaitools.app/tool/mindstudio) | 1,793,337 | +14.2% | Contact for Pricing | No-code builder for custom AI agents and workflows | [.md](https://openaitools.app/tool/mindstudio.md) |
| 8 | [Runable](https://openaitools.app/tool/runable) | 1,048,370 | -1.9% | Freemium | One AI agent to build, run and grow the work | [.md](https://openaitools.app/tool/runable.md) |
| 9 | [Dify](https://openaitools.app/tool/dify-ai) | 819,691 | -15% | Freemium | Build, deploy, and govern production-ready agentic AI workflows | [.md](https://openaitools.app/tool/dify-ai.md) |
| 10 | [Open WebUI](https://openaitools.app/tool/open-webui) | 804,534 | -2.8% | Freemium | Self-hosted AI workspace for local and cloud models | [.md](https://openaitools.app/tool/open-webui.md) |

---
Source: https://openaitools.app/compare/hermes-agent-1-vs-runner-h

More Markdown: [Categories](https://openaitools.app/categories.md) · [Traffic rankings](https://openaitools.app/rankings.md) · [llms.txt](https://openaitools.app/llms.txt)
