Agents-OSS
EN
Submit

hermes-agent vs openclaw

Both are catalogued under Tools & Integrations. The figures come from the GitHub API; the assessments are ours.

hermes-agentA self-hosted personal agent that writes its own memory and skills, reachable from a TUI or Telegram.OfficialMITopenclawA single-operator assistant that runs as a local Gateway and reaches you in the chat apps you use.OfficialMIT

At a glance

At a glancehermes-agentopenclaw
LicenseMITMIT
LanguagesPython, TypeScriptTypeScript
DeploymentSelf-hosted / Runs locallySelf-hosted / Runs locally
MaturityEstablishedGrowing
Stars231k386k
Star growth over the last 7 days——
Forks45.9k81.2k
Open issues32.2k5.5k
Last commit16 Aug 202616 Aug 2026
ActivityActiveActive

What each one does

hermes-agent

Hermes Agent is Nous Research's own agent: a terminal UI plus a single gateway process that carries the same conversation into Telegram, Discord, Slack, WhatsApp, Signal and Email, with a cron scheduler, isolated subagents, and seven terminal backends from local and Docker to Modal and Vercel Sandbox. Its distinguishing piece is a closed learning loop — the agent curates its own memory on periodic nudges, creates skills after complex tasks, and searches past sessions through FTS5 with LLM summarization — which means the state that makes it useful accumulates under `~/.hermes`, outside your version control, and needs occasional pruning. It is an assistant you run and configure rather than a library you build on: the README documents `hermes` subcommands and slash commands, not an embedding API, so it is a poor fit if you wanted an agent loop to call from your own code. Putting a shell-capable agent behind chat platforms also makes the command-approval and DM-pairing settings load-bearing rather than optional.

Full entry →

openclaw

OpenClaw installs a Gateway on your own machine and makes it the local control plane for sessions, tools, events and channel connections, so the Control UI, CLI, TUI and every connected messaging channel drive the same assistant. Models can be hosted or local, and the project expects new capabilities to arrive as plugins built on the plugin SDK rather than as changes to the core. The constraints are stated plainly in the README: it is designed for a single operator, tools run on the host for the main session unless you configure sandboxing, and DM-capable channels leave the assistant reachable by unknown senders until you approve a pairing with `openclaw pairing approve <channel> <code>`. The README tells you to read the security, exposure and sandboxing guides before connecting other users or exposing the Gateway remotely, which is a fair signal that shared or multi-user deployment is not the case it was built for.

Full entry →

What you can do

hermes-agent

  • Run it on a server and talk to it from your phone — hermes gateway setup then hermes gateway start serves Telegram, Discord, Slack, WhatsApp, Signal and Email from one process, with voice memo transcription and conversation continuity across platforms. /model, /compress and /undo work on both sides, but the two interfaces are not identical: usage insights are /insights [--days N] in the CLI versus /insights [days] in chat, and interrupting is Ctrl+C in the TUI versus /stop in a message.
  • Let the environment hibernate between sessions — Terminal backends cover local, Docker, SSH, Singularity, Modal, Daytona and Vercel Sandbox. Daytona and Modal add serverless persistence: the agent's environment hibernates when idle and wakes on demand, so an idle deployment costs close to nothing.
  • Change model or tool provider without touching code — hermes model selects provider and model — OpenRouter, OpenAI, Nous Portal or your own endpoint. hermes setup --portal runs the OAuth login and enables the Tool Gateway, routing web search (Firecrawl), image generation (FAL), TTS (OpenAI) and a cloud browser (Browser Use) through one subscription; the gateway is per-backend, so you can still supply your own key per tool. hermes portal info prints what is wired up.
  • Carry an OpenClaw setup across — hermes claw migrate imports SOUL.md, MEMORY.md and USER.md entries, user-created skills into ~/.hermes/skills/openclaw-imports/, the command allowlist, messaging configs and allowlisted API keys. --dry-run previews the plan and --preset user-data migrates without secrets; hermes setup also detects ~/.openclaw on first run.
  • Schedule unattended runs and fan work out to subagents — The built-in cron scheduler takes tasks written in natural language and delivers results to any connected platform; the setup is documented under docs/user-guide/features/cron. Parallel workstreams go to isolated subagents, and Python scripts that call tools over RPC collapse a multi-step pipeline into one zero-context-cost turn. Note that the README's command list exposes no scheduling subcommand — the entry point is the conversation itself.

openclaw

  • Talk to it from the chat apps you already use — Channels connect WhatsApp, Telegram, Slack, Discord, Google Chat, Signal and iMessage to the same Gateway. Inbound messages are treated as untrusted input, and unknown senders on DM-capable channels stay unpaired until you run openclaw pairing approve <channel> <code>.
  • Go from install to a working assistant in three commands — curl -fsSL https://openclaw.ai/install.sh | bash (or iwr -useb https://openclaw.ai/install.ps1 | iex on Windows PowerShell) provisions a Node runtime when needed; then openclaw onboard --install-daemon verifies model access and creates the workspace, and openclaw dashboard opens the Control UI. Installing via npm install -g openclaw@latest instead requires Node 22.22.3+, 24.15+ or 25.9+.
  • Drive the same session from terminal or browser — The Control UI, CLI and TUI are all clients of the Gateway, and openclaw gateway status reports whether the local Gateway is running.
  • Extend it without forking the core — Tools, skills and plugins are the extension points; the README states that new capabilities usually belong in plugins built on the plugin SDK and shared through ClawHub rather than merged into the main repository.
  • Attach device hardware through companion apps and nodes — Companion apps and device nodes connect to the Gateway to add voice, Canvas, camera, screen and device-local actions, but only on supported platforms — the per-platform setup is documented separately under docs.openclaw.ai/platforms and docs.openclaw.ai/nodes, not in the core install flow.

Other comparisons