Skip to main content
πŸ“– The AI Tool Bible

Hermes One vs ZeroClaw

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

Tagline
Hermes One
Self-improving AI assistant with tool use, multi-platform messaging, and a closed learning loop.
ZeroClaw
ZeroClaw is a personal AI assistant that runs as a single Rust binary on the user's own machine.
Pricing
Hermes One
FreeΒ· Free, MIT-licensed; you pay your own model inference costs
ZeroClaw
Free
API
Hermes One
Yes
ZeroClaw
Yes
Platforms
Hermes One
macoswindowslinuxcli
ZeroClaw
macoslinuxwindows
Open source
Hermes One
Yes Β· MIT
ZeroClaw
Yes
GitHub stars
Hermes One
262,998
checked 2026-11-13
ZeroClaw
β€”
Last GitHub push
Hermes One
2026-11-13
ZeroClaw
β€”
First commit
Hermes One
2025-07
ZeroClaw
β€”
Hacker News stories
Hermes One
0
checked 2026-11-13
ZeroClaw
0
checked 2026-10-23
Earliest Wayback capture
Hermes One
2026-08-05
earliest archived capture of the site, not a launch date
ZeroClaw
β€”
Company
Hermes One
Nous Research
ZeroClaw
β€”
Model used
Hermes One
Multi-model (BYO via OpenRouter/OpenAI/Anthropic/Gemini/xAI/Ollama)
ZeroClaw
Bring-your-own: Claude, OpenAI, or local models via Ollama / llama.cpp
Editorial score
Hermes One
7.2 / 10
ZeroClaw
β€”
Use cases
Hermes One
autonomous-agentschat-opstask-automationresearch-agentspersonal-assistant
ZeroClaw
Auditable shell automationUnattended homelab jobs
Pros
Hermes One
  • Autonomous skill creation and self-improving skills during use.
  • Native connectors for Telegram, Discord, Slack, WhatsApp, Signal, and CLI via a single gateway.
  • Model-agnostic support for cloud APIs and local endpoints like Ollama and LM Studio.
  • Parallel subagent spawning for isolated workstreams.
  • Deep memory with FTS5 session search and LLM summarization for cross-session recall.
ZeroClaw
  • The vendor says that ZeroClaw is a single native binary that requires no additional runtime environments like Node, JVM, or Python.
  • The ZeroClaw agent has fast cold starts and low memory usage.
  • ZeroClaw supports over 70 LLM providers and over 30 communication channels.
  • ZeroClaw is open source with permissive licensing.
  • ZeroClaw defaults to supervised autonomy where medium-risk actions require approval and high-risk actions are blocked.
Cons
Hermes One
β€”
ZeroClaw
  • Users must supply their own LLM provider costs or hardware to run local models.
Website
Hermes One
hermesone.org

Editorial score: rule-based, 0–10, from AI-assisted profile inputs (see /methodology) β€” not a user rating; β€œβ€”β€ means unscored. β€œNot listed” means we have no record of it, not that it is absent. GitHub figures and prices carry the date they were checked or captured; prices are shown as published, unconverted.

Pick Hermes One if
  • βœ… Autonomous skill creation and self-improving skills during use.
  • βœ… Native connectors for Telegram, Discord, Slack, WhatsApp, Signal, and CLI via a single gateway.
  • βœ… Model-agnostic support for cloud APIs and local endpoints like Ollama and LM Studio.
  • βœ… Parallel subagent spawning for isolated workstreams.
Pick ZeroClaw if
  • βœ… The vendor says that ZeroClaw is a single native binary that requires no additional runtime environments like Node, JVM, or Python.
  • βœ… The ZeroClaw agent has fast cold starts and low memory usage.
  • βœ… ZeroClaw supports over 70 LLM providers and over 30 communication channels.
  • βœ… ZeroClaw is open source with permissive licensing.