Agents-OSS
EN
Submit

hermes-agent vs skills

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.OfficialMITskillsGoogle's own Agent Skills for Google Cloud, Ads and AnalyticsOfficialApache-2.0

At a glance

At a glancehermes-agentskills
LicenseMITApache-2.0
LanguagesPython, TypeScriptPython
DeploymentSelf-hosted / Runs locallyRuns locally
MaturityEstablishedGrowing
Stars231k18.3k
Star growth over the last 7 days——
Forks45.9k1.4k
Open issues32.2k32
Last commit16 Aug 202614 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 →

skills

Over a hundred skill directories of Google's own written guidance, installed selectively with `npx skills add google/skills`. The bulk sits under `skills/cloud` — GKE, BigQuery, Agent Platform, the six Well-Architected pillars — while `skills/ads` and `skills/analytics` cover the Google Ads API, the Mobile Ads and IMA SDKs and the two Google Analytics APIs. Depth is uneven: `skills/cloud/gke-*` accounts for twenty-nine directories on its own, Cloud Run and Firebase get one each, and the README labels the repository as under active development. A stack on neither Google Cloud nor Google's ads and analytics products gets nothing here, and app-side coverage stops at the Mobile Ads SDK — Android, Flutter, Dart, Genkit and ADK skills are separate repositories the README only links to.

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.

skills

  • Install only the skills you want — npx skills add google/skills lets you select which skill directories to install rather than dropping the whole catalogue into the agent; the README's Available Skills section, between its BEGIN SKILLS and END SKILLS markers, lists every one by product area with a link to its directory.
  • Register it as a harness plugin — claude plugin marketplace add google/skills then claude plugin install <plugin>@google-plugins installs bundles that pair skills with MCP servers; Codex uses codex plugin marketplace add google/skills and its /plugins browser, and Antigravity CLI takes agy plugin install https://github.com/google/skills/<plugin-path>.
  • Hand an agent the GKE material — The skills/cloud/gke-* set covers cluster creation, ComputeClasses, the cluster autoscaler, multi-tenancy, networking, storage and upgrades, with failure modes split into their own skills such as gke-ai-troubleshooting-jobset-interruption and gke-ai-troubleshooting-tpu-vbar-oom.
  • Make it write the queries — cloud-logging-query-generation produces Logging Query Language, cloud-monitoring-list-time-series-request assembles ListTimeSeries requests and cloud-monitoring-chart-generation builds charts, while bigquery-basics, spanner-basics, bigquery-bigframes and managed-airflow-dag-authoring cover the data side.
  • Work the Ads and Analytics APIs — skills/ads holds thirteen skills — google-ads-api-quickstart, google-ads-api-account-diagnostics, google-ads-api-mcp-setup, data-manager-api-setup / -event-ingestion / -audience-ingestion, five Google Mobile Ads SDK skills including google-mobile-ads-android-migrate-to-next-gen, and ima-sdk-client-side / ima-dai-sdk for video — and skills/analytics adds google-analytics-admin-api-basics and google-analytics-data-api-basics, all of it outside the skills/cloud tree.

Other comparisons