Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Hermes Agent vs nanobot

Hermes Agent (Nous Research) and nanobot (HKUDS) side by side on public data, as of Nov 20, 2026.

Hermes Agent has 5.0x the weekly package downloads of nanobot (88.2K against 17.7K). Hermes Agent has 5.3x the GitHub stars of nanobot (265K against 50.2K). Hermes Agent shipped 20 stable releases in the past 90 days. nanobot shipped 3 stable releases in the past 90 days.

Which should you choose?

Choose Hermes Agent if

  • you prefer the more widely used tool, with more docs and answers around (Gid Score 63 against 40)
  • you want frequent updates (20 stable releases in 90 days against 3)

Choose nanobot if

  • you need to run local models

Built from documented features, official prices, status pages and usage data on this page; it does not judge output quality.

Side-by-side numbers

Metric Hermes Agentnanobot
Gid Score6340
Usage data as ofNov 19Nov 19
Rank by Gid Score#13#87
Downloads, last 7 days88.2K17.7K
Downloads, 7-day changeup 34.8%down 24.4%
Downloads, 30-day change—up 14.8%
VS Code installs——
Marketplace rating——
GitHub stars265K50.2K
Homebrew installs, 30 days2,185—
Hacker News mentions, 30 days460
Latest stable release0.23.2 · 4d ago0.4.1 · 14d ago
Stable releases, 90 days203
Terminal-Bench (best run)——
PriceFree (OSS)Free (OSS)
LicenseMITMIT
First releasedFebruary 2026February 2026
InterfacesCLI, Messaging apps, DesktopCLI, Web app, Messaging apps, SDK, Self-hosted
ModelsAny model: Nous Portal, OpenRouter, OpenAI and custom endpoints; a Claude Pro or Max plan through an experimental plugin—

A dash means there is no public data for that metric as of Nov 20, 2026.

Trends

Downloads per daynpm + PyPI, 7-day average
Hermes Agentnanobot
GitHub starsrunning total
Hermes Agentnanobot

Hermes Agent

Open-source agent from Nous Research, described by its makers as self-improving, that keeps persistent memory, creates and refines skills from experience, runs scheduled automations, and works from a terminal interface or messaging apps such as Telegram, Discord, Slack and WhatsApp. It can run locally or on Docker, SSH, Modal, Daytona and Vercel Sandbox backends, and has a desktop app.

Pricing: Free and open source (MIT); users pay their chosen model providers (Nous Portal, OpenRouter, OpenAI or custom endpoints).

Latest release 0.23.2:

  • Desktop chats created by an August build with a bare custom provider can send again after updating.
  • A Desktop or TUI reply that streamed beside a todo or memory call now settles instead of leaving the Stop button up.
  • A crash mid-stream on Telegram and other edit-streaming chats no longer shows a duplicate "Recovered reply"; a word holding a key prefix mid-word (program_id) is shown on time again.
  • Desktop no longer loses or scrambles what you type while it starts and resumes your last chat.

Full Hermes Agent profile

nanobot

A lightweight, self-hosted personal agent runtime in Python that runs in a web UI, a terminal or chat apps, using shell, files, web, MCP and sub-agents, with long-term memory and scheduled automations.

Pricing: Free MIT-licensed self-hosted software; users supply their own model providers or local models.

Latest release 0.4.1:

  • Fix TLS certificate verification, sandboxed shell execution and workspace permissions for queued inputs.
  • Keep idle maintenance from blocking active work or incorrectly refusing an update. Improve retry, reconnection and recovery behavior, and preserve native provider state through compaction.
  • Add a file-context graph with file previews, local Markdown links and recent context snapshots. Switching topics keeps each conversation's context separate.
  • Share syntax highlighting across code, source previews and read-only diffs, with complete source copying and plain-text fallbacks.

Full nanobot profile

Hermes Agent vs nanobot: common questions

Which is more popular, Hermes Agent or nanobot?

Hermes Agent has a Gid Score of 63 against 40 for nanobot. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.

Do Hermes Agent and nanobot support local models?

nanobot documents support for local models; Hermes Agent's documentation does not.