# Hermes vs OpenClaw: Which Self-Hosted Personal Agent to Run (October 2026) > Hermes vs OpenClaw, rebuilt from both repos in October 2026: default security posture, memory, install cost, project health, and when to pick each one. Hermes vs OpenClaw is the comparison to make if you want an AI agent you can text from Telegram, running on a box you control. Both are MIT-licensed, both work with any model, and both are huge: on October 2, 2026, OpenClaw had 391,188 GitHub stars and Hermes Agent 250,673. The comparisons that rank for this query were mostly written in spring, and several of their headline claims no longer hold. So I rebuilt this one from each project's own repo and docs at their latest releases (OpenClaw 2026.9.7, Hermes Agent v0.21.5), pulled the health and security numbers straight from GitHub and NVD, and installed both into a scratch directory to measure them. **The short answer:** Pick OpenClaw if you want the widest set of chat apps and device apps, conservative release channels and operator roles for a small team. Pick Hermes Agent if you want small, readable memory, skills it writes and prunes itself, Modal or Daytona execution, no telemetry, and a paid managed option from the same vendor. Both can now run several agents behind one gateway. Whichever you pick, it runs the agent's shell commands on your host by default, so switch on the container backend before you connect a chat app. ## Hermes vs OpenClaw at a glance (checked October 2, 2026) Every cell comes from the project's own repo, docs or API at the release in the first row, except the advisory row (GitHub and NVD). | | OpenClaw | Hermes Agent | | ------------------------------- | ----------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | | Latest release | 2026.9.7 stable (Sep 30); extended-stable 2026.8.34 (Oct 2) | v0.21.5 (Sep 24) | | Steward, license | OpenClaw Foundation, a 501(c)(3); MIT | Nous Research; MIT | | Stack | TypeScript on Node 24.16+ or 26.1+ | Python; the installer brings its own Python, Node.js, ripgrep and FFmpeg | | Process shape | A Gateway daemon stays up; CLI, TUI and web Control UI attach to it | A CLI/TUI you launch; the gateway is an optional background process for chat apps and cron | | Documented minimum | 1 GB RAM, 1 core, 500 MB disk; 2 GB+ recommended | 1 GB RAM, 1 core, 500 MB disk; 2–4 GB once browser tools run | | Chat platforms in docs | 32 catalog entries | 28 platforms | | Native apps | Companions for macOS, Windows, Linux, iOS and Android; device nodes add voice, camera and screen | Desktop app: downloads for macOS (Apple Silicon) and Windows, Linux via the terminal installer; Android via Termux (Tier 2) | | Several agents at once | Many isolated agents inside one gateway, routed by bindings | One profile per agent; one multiplexing gateway serves every profile by default, and `profile_routes` sends chats on a shared bot to a profile | | Memory | Markdown files (`MEMORY.md`, `USER.md`, daily notes) plus indexed search and background consolidation | `MEMORY.md` (2,200 chars) and `USER.md` (1,375 chars) in the prompt, plus SQLite full-text search over every session | | Self-learning | Skill Workshop, default mode `auto` | Writes and patches its own skills by default; a curator archives unused ones | | Agent shell commands by default | On the host, no prompts for the owner; sandbox `off` | On the host (`local` backend); `smart` approvals, where a helper model auto-approves "low-risk" commands | | Phones home | Daily version check; feature stats opt-in | Nothing, per its FAQ | | Official hosting | None | Hermes Cloud, from $0.56/day while running | | Published security advisories | 722 GitHub advisories, 14 critical | 0 GitHub advisories; 39 NVD CVEs filed by a third party | ## Which one should you run? In Hermes Agent vs OpenClaw, choose by the feature you can't live without, not by star count. Each project shipped 18 stable releases between July 1 and October 2, so a gap that matters today may close in a month, but the points below are structural. ### Pick OpenClaw if - **Your chat app is only on its list.** Nextcloud Talk, Nostr, Synology Chat, Tlon (Urbit), Twitch and three Zalo connection paths are in the [OpenClaw channel catalog](https://github.com/openclaw/openclaw/blob/v2026.9.7/docs/channels/index.md) and absent from Hermes's platform table. - **You want your phone to be a device, not just a chat window.** The [OpenClaw README](https://github.com/openclaw/openclaw) lists companion apps and nodes for voice, Canvas, camera and screen actions. Hermes runs on Android only through Termux, which its [platform support page](https://github.com/NousResearch/hermes-agent/blob/main/website/docs/getting-started/platform-support.md) rates Tier 2. - **You already pay for Claude.** OpenClaw can run agent turns through the Claude Code CLI you're signed into. Per [OpenClaw's Anthropic provider page](https://github.com/openclaw/openclaw/blob/main/docs/providers/anthropic.md), Anthropic counts that use against your subscription's limits. Hermes can't use a Claude Pro login at all (details in the cost section). - **You update cautiously.** OpenClaw has [four update channels](https://github.com/openclaw/openclaw/blob/main/docs/install/development-channels.md): stable, beta, dev, and extended-stable, a trailing supported month that never applies itself. - **A small trusted team shares it.** Named operator roles cap what each teammate's connection can do. OpenClaw's [trust model](https://github.com/openclaw/openclaw/blob/v2026.9.7/docs/gateway/security/trust-model.md) is explicit that this is a guardrail, not tenant isolation. ### Pick Hermes Agent if - **You want memory you can audit in a minute.** About 3,575 characters sit in the prompt; everything else is searchable history. Both memory and skill writes can be put behind an approval gate (config below). - **You want commands to run on Modal or Daytona.** Hermes has [seven terminal backends](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/README.md), and the Modal and Daytona environments hibernate between tasks. OpenClaw's sandbox backends are Docker, Podman, SSH, OpenShell and Crabbox. - **You want email, Home Assistant, DingTalk, SimpleX or ntfy as a chat surface.** They're in [Hermes's messaging table](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/user-guide/messaging/index.md). By OpenClaw's own account, it handles inbound email as an automation trigger rather than a conversation. - **You want nothing phoning home.** The [Hermes FAQ](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/reference/faq.md) says it collects no telemetry. OpenClaw's [telemetry page](https://github.com/openclaw/openclaw/blob/main/docs/gateway/telemetry.md) documents a daily version check by default; `update.checkOnStart: false` turns it off. - **You want a managed fallback from the same vendor.** Nous sells Hermes Cloud (prices below). The OpenClaw Foundation runs no hosted service. - **Your tooling is Python.** Hermes's core, plugins and research tools (trajectory export, a batch runner) are Python. Several agents behind one front door no longer separates them. OpenClaw's [multi-agent routing](https://github.com/openclaw/openclaw/blob/main/docs/concepts/multi-agent.md) runs isolated agents in one gateway and uses bindings to send a given WhatsApp number or Slack workspace to a given agent. Hermes's [multi-profile gateway docs](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/user-guide/multi-profile-gateways.md) for v0.21.5 make one multiplexing gateway serve every profile by default (`gateway.multiplex_profiles`), call per-profile gateways "a temporary shim, not a supported topology", and route chats on one shared bot to different profiles with `gateway.profile_routes`. ### Run neither as-is if Strangers or semi-trusted people will message the bot. Both projects support exactly one trust boundary per running instance: OpenClaw wants separate gateways, ideally on separate OS users or hosts, for users who don't trust each other, and Hermes's [security policy](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/SECURITY.md) calls it a single-tenant personal agent. One instance per person is the supported shape for both. If neither fits, our [OpenClaw alternatives roundup](/blog/openclaw-alternatives) covers the other options. ## Six claims in other comparisons that are now wrong Each row was checked against the primary source on October 2, 2026. | Claim you'll see | What the primary source says now | | ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | OpenClaw skills are static; only Hermes learns | OpenClaw's [self-learning docs](https://github.com/openclaw/openclaw/blob/v2026.9.7/docs/tools/self-learning.md) (added July 2026) turn corrections and successful work into skills, default mode `auto` | | Hermes has zero CVEs | [NVD's CVE API](https://services.nvd.nist.gov/rest/json/cves/2.0?keywordSearch=hermes-agent) returns 39 CVEs for NousResearch hermes-agent, published April 27 to September 3, 2026 | | OpenClaw has a commercial SaaS; Hermes has no hosting | Reversed. The OpenClaw README says the Foundation has "no paid tier, hosted service, or token"; [Hermes Cloud](https://portal.nousresearch.com/cloud) is Nous's paid hosting | | OpenClaw covers 50+ platforms, Hermes 6 | 32 entries in OpenClaw's catalog vs 28 platforms in Hermes's table | | OpenClaw's workspace fences the agent in | The workspace is only the default working directory. [OpenClaw's docs](https://github.com/openclaw/openclaw/blob/main/docs/concepts/multi-agent.md) say absolute paths reach the rest of the host unless sandboxing is on | | CVE-2026-25253 was a skill-sandbox path traversal, CVSS 9.1 | [NVD CVE-2026-25253](https://nvd.nist.gov/vuln/detail/CVE-2026-25253): versions before 2026.1.29 took a `gatewayUrl` from a query string and connected without prompting, sending the token; CVSS 8.8 | Two more drift quickly enough to re-check yourself: Hermes's approval default is now `smart`, not `manual`, and Hermes is past 250,000 stars, not 22,000. ## How do memory and self-learning differ? Hermes keeps a deliberately small memory inside every prompt and searches everything else on demand. OpenClaw keeps larger Markdown files on disk and consolidates them in the background. Both now write their own skills by default, which is the part you should decide to gate. **Hermes.** [Its memory docs](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/user-guide/features/memory.md) cap `MEMORY.md` at 2,200 characters (about 800 tokens) and `USER.md` at 1,375 (about 500). When a write would overflow, the tool returns an error and the agent must merge or delete entries first. Every CLI and chat session also goes into a SQLite database with full-text search, and the docs put a query at about 20 ms. After a turn, a background review may save a memory or patch a skill; you can point that review at a cheaper model under `auxiliary.background_review`, which the docs say costs 3–5× less. The [curator](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/user-guide/features/curator.md) runs at most every 7 days, marks agent-written skills stale after 14 unused days and archives them after 30. Its LLM merge pass is off by default. If you want semantic recall on top, seven external memory plugins (Honcho, Mem0 and others) run alongside the built-in files. **OpenClaw.** [The OpenClaw memory overview](https://github.com/openclaw/openclaw/blob/main/docs/concepts/memory.md) uses `MEMORY.md`, an optional `USER.md` and dated daily notes. Today's and yesterday's notes load on `/new`, older ones are searchable, and a background "dreaming" sweep distills notes into `MEMORY.md`. There's no hard cap: when `MEMORY.md` outgrows the prompt budget, the copy injected into context is truncated while the file stays whole, so check `/context list` or `openclaw doctor` now and then. Self-learning reviews a turn only after at least 10 model iterations and 30 quiet seconds. In `auto` mode those edits skip proposals and rollback snapshots, so your backups are the undo button. If you'd rather approve what the agent learns, here are the switches: ```yaml # Hermes: ~/.hermes/config.yaml memory: write_approval: true # stage memory writes; review with /memory pending skills: write_approval: true # stage skill writes; review with /skills pending and /skills diff ``` ```bash # OpenClaw: drafts wait for you instead of applying openclaw config set skills.workshop.autonomous.mode propose ``` Two failure modes the docs describe: - **"It said it would remember, then forgot."** In Hermes, memory only persists when the model actually calls the `memory` tool. The docs single out small local models, roughly under 30B parameters, for confirming a save they never made. Check `~/.hermes/memories/MEMORY.md`; if the entry isn't there, use a stronger model for setup. - **A chat that never ends.** Hermes treats a Telegram or Discord chat as one continuous session that survives restarts. Without a `/new` at natural breaks, compaction keeps re-running over a growing history and the memory loop rarely fires. ## Is Hermes or OpenClaw safer? Neither is safe by default on a machine that holds your secrets. Out of the box both run the agent's shell commands on the host, and both projects say plainly that real containment comes from the operating system, not from approval prompts. **The defaults, from each project's own docs:** - **OpenClaw.** [Sandboxing](https://github.com/openclaw/openclaw/blob/v2026.9.7/docs/gateway/sandboxing/modes-scope-and-backend.md) defaults to `off`. For the trusted single operator, host commands run "without approval prompts" (`security="full"`, `ask="off"`), per the trust model. By default, any tool-enabled agent running unsandboxed can list and read every other agent's sessions on the same gateway. DM pairing for unknown senders is on. - **Hermes.** The default terminal backend runs commands directly on the host. The default approval mode, `smart`, lets a helper model auto-approve commands it judges low-risk; a hardline blocklist (root wipes, fork bombs, raw disk writes) can't be overridden even in `--yolo`. With no allowlist configured, the gateway denies every user. Hermes's [security policy](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/SECURITY.md) states: "The only security boundary against an adversarial LLM is the operating system." It also says running the default local backend with untrusted input, such as inbound chat, email or web content, is outside its supported posture. **The record, checked October 2, 2026:** - **OpenClaw** has published 722 [GitHub security advisories](https://github.com/openclaw/openclaw/security/advisories) since January 2026: 14 critical, 249 high, 390 medium, 69 low. Seventy-five came out in September 2026 alone. Its skill registry has a history too: Koi Security's ClawHavoc report found 341 malicious skills in February, and after ClawHub added VirusTotal and ClawScan checks, [Unit 42 (June 23, 2026)](https://unit42.paloaltonetworks.com/openclaw-ai-supply-chain-risk/) still found five unblocked ones, including one padded to slip past scanner size limits. OpenClaw deleted them. - **Hermes** has zero GitHub advisories. NVD lists 39 CVEs for hermes-agent, all filed by VulDB as the numbering authority, with CVSS 3.1 scores up to 7.3. In 28 of them, the record says the vendor didn't respond to the disclosure. [CVE-2026-14625](https://nvd.nist.gov/vuln/detail/CVE-2026-14625), a protection-mechanism failure in the TUI gateway's `shell.exec` up to 0.15.2, is a representative entry. Don't read 722 versus 39 as a safety score. OpenClaw's maintainers publish their own advisories, so the count also measures a working disclosure pipeline; Hermes's public record comes from a third party, often without vendor confirmation. What the numbers do tell you: OpenClaw reports what it fixed, while with Hermes you'll track issues and CVE records yourself. **What to change on day one.** Run the agent on a box or VM that doesn't hold your personal keys, then add tool sandboxing: ```yaml # Hermes: ~/.hermes/config.yaml terminal: backend: docker # shell and file tools run in a hardened container container_persistent: false # optional: a fresh container per chat ``` ```json5 // OpenClaw: ~/.openclaw/openclaw.json { agents: { defaults: { sandbox: { mode: 'all', scope: 'session', workspaceAccess: 'rw' } } } } ``` Then the three things that bite after you flip those switches: - **OpenClaw sandbox runs fail immediately.** It won't fall back to a stock image; you have to build `openclaw-sandbox:bookworm-slim` first. npm installs use the inline `docker build` in the [images and setup page](https://github.com/openclaw/openclaw/blob/v2026.9.7/docs/gateway/sandboxing/images-and-setup.md). - **OpenClaw's sandboxed tools can't reach the internet.** The Docker backend defaults to `network: "none"`. Give network access only to agents that need it, via `agents.defaults.sandbox.docker.network`. - **Hermes's container doesn't cover everything.** Its policy says the terminal backend confines shell and file tools, not MCP servers, plugins or skill loading, which still run in the agent's own process. If the agent reads email, the open web or group chats, run the whole thing in the official Docker image instead. For the wider pre-launch list, see our [AI agent security checklist](/blog/ai-agent-security-checklist). ## What does each cost to run? The software is free; you pay for a machine with 1–2 GB of RAM and for model tokens. OpenClaw's deploy guides run from no-cost options (Oracle Cloud's Always Free ARM tier, the free tiers on Render and Fly) and a one-time $35–80 Raspberry Pi to a $6-a-month DigitalOcean droplet, the cheapest paid VPS they quote. Inference runs from nothing on a local model to whatever your provider charges. **Disk and install.** I installed both into a scratch directory on an Apple Silicon Mac on October 2, 2026. `npm install openclaw@2026.9.7 --ignore-scripts` added 343 packages and 728 MB of `node_modules` (404 MB of it the `openclaw` package), before the Node runtime itself. Hermes v0.21.5, synced from its lockfile with the `all` extra, came to 103 Python packages: a 230 MB virtualenv, 210 MB of source and a 50 MB Python, before the Node.js, ripgrep and FFmpeg its installer adds. On Docker Hub, the compressed amd64 images are 970 MB for Hermes `latest` and 1.23 GB for OpenClaw `latest`, whose `slim` tag is the same size; OpenClaw's extended-stable 2026.8.34 image is 535 MB. Disk won't decide this. **RAM and the box.** Both document the same 1 GB, 1-core floor (OpenClaw in its [Raspberry Pi guide](https://github.com/openclaw/openclaw/blob/main/docs/install/raspberry-pi.md), Hermes in its [Docker guide](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/user-guide/docker.md)), and both recommend 2 GB or more; Hermes ties that to running browser tools. OpenClaw's [DigitalOcean guide](https://github.com/openclaw/openclaw/blob/main/docs/install/digitalocean.md) prices the 1 GB droplet at about $6 a month and warns against Marketplace 1-click images you haven't reviewed. **Install and connect Telegram** (both installers also have a PowerShell variant for Windows): ```bash # OpenClaw: installs Node if missing, then starts onboarding curl -fsSL https://openclaw.ai/install.sh | bash openclaw channels add --channel telegram --token openclaw pairing approve telegram # the code your bot sends you on first DM # Hermes Agent: needs git; brings its own Python, Node.js, ripgrep, FFmpeg curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes gateway setup # pick Telegram, paste the bot token hermes gateway install && hermes gateway start # run it as a user service hermes pairing approve telegram ``` **Models.** Both take any OpenAI-compatible endpoint plus dozens of named providers. What differs is which consumer subscriptions they can use: | Subscription you already have | OpenClaw | Hermes Agent | | ----------------------------- | ------------------------------------------------------ | ------------------------------------------------------------------------------- | | Claude Pro | Via the Claude Code CLI; draws from your plan's limits | Not usable; Pro can't take the OAuth path, so use an API key | | Claude Max | Via the Claude Code CLI | OAuth works, but only purchased extra usage is billed, never the base allowance | | ChatGPT / Codex | Codex OAuth, run through the Codex app-server runtime | ChatGPT OAuth with Codex models; plan-quota behavior undocumented | | Neither | API keys, OpenRouter, local models | API keys, OpenRouter, local models, or Nous Portal | The Hermes column comes from [its provider docs](https://github.com/NousResearch/hermes-agent/blob/v2026.9.24/website/docs/integrations/providers.md). [Nous Portal](https://hermes-agent.nousresearch.com/) has a free tier limited to free models; Plus is $20 a month with $22 of credits, Super $100 and Ultra $200. **Local models.** Hermes refuses any model with less than 64,000 tokens of context, and Ollama defaults to 4,096 on GPUs with under 24 GB of VRAM, so a fresh Ollama setup fails at startup. The fix from the Hermes docs: ```bash OLLAMA_CONTEXT_LENGTH=64000 ollama serve ``` OpenClaw's managed llama.cpp recipes also use a 64K context and start at 8 GiB of host memory, per its [local models page](https://github.com/openclaw/openclaw/blob/main/docs/gateway/local-models.md). Its DigitalOcean guide adds that local inference won't fit on a 1 GB droplet, so plan on a hosted model there. ## OpenClaw vs Hermes: which project is healthier? Both are among the most active repositories on GitHub. The difference is how much of the incoming work gets merged. | GitHub API, October 2, 2026 | OpenClaw | Hermes Agent | | -------------------------------------------- | ---------------- | ------------------------------------------------ | | Stars / forks | 391,188 / 82,246 | 250,673 / 53,682 | | Repo created | Nov 24, 2025 | Jul 22, 2025 (first tagged release Mar 12, 2026) | | Contributors (API, anonymous included) | ~3,470 | ~4,160 | | Stable releases since July 1, 2026 | 18 | 18 | | Pull requests opened / merged, Sep 2 – Oct 1 | 20,507 / 16,707 | 22,874 / 4,661 | | Open pull requests / open issues | 3,252 / 5,894 | 33,863 / 14,439 | | Commits on `main` past the latest release | 1,911 | 5,710 | OpenClaw merged about four PRs for every five opened in that window. Hermes merged about one in five, and carries a backlog of nearly 34,000 open pull requests. If you plan to contribute a fix, expect it to wait longer on Hermes. The last row is a trap worth fixing on day one. On a Hermes source install, `hermes update` pulls the latest commits from git, which means `main`, not the latest release. When I ran `hermes --version` on v0.21.5, it reported the install as 5,710 commits behind. Hermes's docs on `main` describe a `hermes update --set-channel stable` option, but the v0.21.5 updater doesn't have it yet. On a server, run the Hermes Agent Docker image pinned to a release tag instead, using the commands from the Hermes Docker guide: ```bash # one-time setup wizard, writes keys to ~/.hermes/.env docker run -it --rm -v ~/.hermes:/opt/data nousresearch/hermes-agent:v2026.9.24 setup # the gateway, restarted with the host docker run -d --name hermes --restart unless-stopped \ -v ~/.hermes:/opt/data \ nousresearch/hermes-agent:v2026.9.24 gateway run ``` Leave off the `-p 8642:8642` port mapping you'll see in the Hermes Docker guide unless you need its API server; the guide says it's optional when you only use chat apps. On OpenClaw, npm's `latest` already means the stable channel, and `openclaw update --channel extended-stable` holds you a month back. ## How do you switch, or try both? Both ship importers, so a wrong first pick costs an afternoon, not your memory. Preview before applying (the OpenClaw import expects a fresh OpenClaw setup): ```bash # OpenClaw → Hermes: imports SOUL.md, memories, skills, allowlists; secrets only with --migrate-secrets hermes claw migrate --dry-run # Hermes → OpenClaw: model config, MCP servers, SOUL.md, AGENTS.md, memories, skills openclaw migrate hermes --dry-run ``` To run them side by side for a week, give each its own directory or container (`~/.hermes` and `~/.openclaw` don't collide) and its own bot. Hermes's FAQ notes that a bot token serves one running gateway at a time, and the second one to connect fails. After an import that brought over OAuth credentials, OpenClaw's docs say to sign in again on one side so the two aren't sharing one refresh grant. ## Hermes Agent vs Claude Code: different jobs Claude Code is Anthropic's coding agent: it works in your repo from the terminal, IDE, desktop app or browser, and you review its output as diffs and pull requests. Hermes Agent and OpenClaw are general assistants that live in your chat apps, remember you across weeks, and run scheduled jobs on any model. The lines are blurring. Claude Code's [Channels](https://code.claude.com/docs/en/channels) (a research preview) push Telegram, Discord and iMessage messages into a running session, but they arrive only while that session is open, and its scheduled Routines run in Anthropic's cloud. Use Claude Code for repository work you'll review. Use Hermes or OpenClaw for the assistant you message about inboxes, research, reminders or your home. To combine them, OpenClaw can use your Claude Code login as its runtime; Hermes needs an API key or a Max plan with extra usage. ## Don't want to run a box? Two managed routes exist, and only one comes from the projects themselves. - **Hermes Cloud.** Nous's [hosting page](https://portal.nousresearch.com/cloud) prices a Medium instance (2 GB RAM, 4 vCPU, 10 concurrent sessions) at $0.56 a day while running and $0.03 stopped, and a Large (4 GB, 8 vCPU) at $1.09. Billing is daily from your Nous credit, inference is extra, and deploying needs $2 in credit or an active subscription. A Medium left running all month comes to about $16.80 before models. - **OpenClaw.** The Foundation offers no hosting. Its docs carry deploy guides for DigitalOcean, Hetzner, Fly, Railway, Render and others, but you operate the result. A third option is ours, and it's a different runtime, not a host for either project. In Octomind Cloud each [octo](/blog/meet-your-octos) is one agent per workstream with its own folder, memory, conversations and scheduled routines, reachable from Telegram, WhatsApp, Slack, Discord, email and GitHub, with models through a built-in gateway so you hold no API keys. Routines fire on a timer, a manual run or a webhook, and the Import page takes an OpenClaw or Hermes folder directly: persona, memories, skills, cron jobs and the Telegram bot come over in one step ([how the import works](/blog/bring-your-agent-over)). The limits are real. An idle machine sleeps after an hour by default and the next message wakes it; keeping it always on costs its memory, about $18 a month on Small. Octos on one machine share a user and a container, so a folder isn't a security wall. And there's no free cloud: Pro is $50 a month, $20 for the first month, with $50 of usage included. ## What this comparison can't tell you - **Answer quality and speed.** I didn't connect either agent to a model, so nothing here says which one completes your tasks better. Latency figures you'll find elsewhere come from single tests on one model. - **Counts across projects.** Channel lists mix vendors, transports and plugin types, and advisory counts reflect disclosure habits as much as bugs. OpenClaw's own Hermes comparison, written by one of the two parties, calls channel counts not directly comparable and advisory counts not a safety score. - **Next month.** At thousands of commits a week, specifics here will date fast. Re-run the `gh api` numbers and re-check the release tags before you commit. - **Neutral ground.** OpenClaw's docs include their own [Hermes comparison](https://github.com/openclaw/openclaw/blob/main/docs/start/why-openclaw/openclaw-and-hermes-agent.md), reviewed against Hermes source from August 27, 2026. It's detailed and well-sourced, and it's also a vendor's view. **[Start with Pro](/pricing)** — if you'd rather hand the box to us, your first month is $20. ## FAQ ### Is Hermes Agent free? Yes. Hermes Agent is MIT-licensed and free to run; you pay only for the model tokens and the machine. Nous Portal adds an optional subscription with a free tier for free models and paid tiers from $20 a month, and Hermes Cloud hosting is billed per day on top. ### Is Hermes a fork of OpenClaw? No. Nous Research built Hermes Agent as its own Python codebase, while OpenClaw is TypeScript, maintained by the OpenClaw Foundation. They share the SKILL.md skill format, and each ships an importer for the other: `hermes claw migrate` and `openclaw migrate hermes`. ### Can I run Hermes and OpenClaw on the same server? Yes, as long as each has its own data directory or container and its own bot tokens. A bot token can be polled by only one gateway process at a time, so Hermes and OpenClaw can't share one. Both document a 1 GB RAM floor, so plan on 2 GB or more for the pair, more with browser tools. ### Which is safer, Hermes Agent or OpenClaw? Neither is safe by default: both run the agent's shell commands on the host until you enable a container backend (`terminal.backend: docker` in Hermes, `agents.defaults.sandbox.mode: "all"` in OpenClaw). OpenClaw has the larger public advisory record because its maintainers publish fixes, while Hermes's 39 CVEs were filed by a third party. Run either on a machine without your personal credentials. ### How do I uninstall Hermes Agent or OpenClaw? For Hermes, stop the gateway (`hermes gateway stop`), preview with `hermes uninstall --dry-run`, then run `hermes uninstall`; add `--full` to remove your data too. For OpenClaw, preview with `openclaw uninstall --dry-run --all`, then run `openclaw uninstall --all` to remove the service, state, workspace and app.