hermes-agent vs nanobot
hermes-agent is much bigger: 255.7k stars against 49.2k. Over the days we have tracked them hermes-agent moved +16.4% and nanobot +6.6%, so hermes-agent is growing faster right now.
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
A self-hostable personal agent with a built-in closed learning loop that creates, persists, and self-improves skills from its own experience.
- Stars
- 255.7k
- Tracked growth
- +16.4%
- Maturity
- ●●●●●
- Last commit
- 12m ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key or Nous Portal subscription
An ultra-lightweight, self-hosted personal agent runtime that pairs a small, readable core with built-in WebUI, persistent memory, automation, and flexible model routing for long-running workflows.
- Stars
- 49.2k
- Tracked growth
- +6.6%
- Maturity
- ●●●●●
- Last commit
- 15m ago
- Language
- Python
- License
- MIT
- Cost to run
- Your API key; optional paid hosting
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | hermes-agent | nanobot |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Related files | ●●●●● Diff + related files |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Approval & allowlist | ●●●●● Basic filters/config |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Skills & config | ●●●●● Presets & automations |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Self-hostable | ●●●●● Fully local possible |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Bring-your-own-key |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-command install | ●●●●● One-command start |
Which one to pick
Pick hermes-agent if…
Continual learning — pick Hermes when you want a self-hosted, continuously learning personal assistant that builds and improves skills across sessions and integrates with messaging platforms.
Pick nanobot if…
Self-hosted — run a lightweight, extendable personal agent locally (or with your own API keys) that includes WebUI, long-term memory, and automation for persistent workflows.
What people want from each one
NousResearch/hermes-agent
Hacker News: Nous Research edits GitHub issue to remove plagiarism claims about Hermes Agent drew 8 points and 1 comments.
HKUDS/nanobot
Hacker News: Nanobot: Ultra-Lightweight Alternative to OpenClaw drew 257 points and 128 comments.
Questions people ask
Is hermes-agent better than nanobot?
Neither one leads on the six capability axes, so the choice comes down to which of them fits the way you already work. hermes-agent is worth picking when continual learning — pick Hermes when you want a self-hosted, continuously learning personal assistant that builds and improves skills across sessions and integrates with messaging platforms.
Which of hermes-agent and nanobot keeps my code private?
hermes-agent: Self-hostable (4/5). nanobot: Fully local possible (5/5).
What does each one cost to run?
hermes-agent: Your API key or Nous Portal subscription. nanobot: Your API key; optional paid hosting.
Full profiles: NousResearch/hermes-agent and HKUDS/nanobot. Everything else in Personal assistants.