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

nanobot vs OpenClaw

nanobot (HKUDS) and OpenClaw (OpenClaw Foundation (nonprofit); created by Peter Steinberger) side by side on public data, as of Nov 20, 2026.

OpenClaw has 175.8x the weekly package downloads of nanobot (3.1M against 17.7K). OpenClaw has 7.9x the GitHub stars of nanobot (395K against 50.2K). Over the last 30 days downloads moved +15% for nanobot and -24% for OpenClaw. nanobot shipped 3 stable releases in the past 90 days. OpenClaw shipped 37 stable releases in the past 90 days.

Which should you choose?

Choose OpenClaw if

  • you want to switch between model providers (12 documented against 5)
  • you want to check in from your phone
  • you prefer the more widely used tool, with more docs and answers around (Gid Score 71 against 40)
  • you want frequent updates (37 stable releases in 90 days against 3)

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 nanobotOpenClaw
Gid Score4071
Usage data as ofNov 19Nov 19
Rank by Gid Score#87#8
Downloads, last 7 days17.7K3.1M
Downloads, 7-day changedown 24.4%up 5.8%
Downloads, 30-day changeup 14.8%down 24.3%
VS Code installs——
Marketplace rating—3.5 / 5 (78)
GitHub stars50.2K395K
Homebrew installs, 30 days—1,317
Hacker News mentions, 30 days0123
Latest stable release0.4.1 · 14d ago2026.10.33 · 2d ago
Stable releases, 90 days337
Terminal-Bench (best run)——
PriceFree (OSS)Free (OSS)
LicenseMITMIT
First releasedFebruary 2026November 2025
InterfacesCLI, Web app, Messaging apps, SDK, Self-hostedMessaging apps, CLI, Desktop, Mobile
Models—Model-agnostic: Claude, OpenAI Codex/GPT, DeepSeek and local models via plugins

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

Trends

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

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

OpenClaw

Open-source personal AI assistant that runs on the user's own machine as a gateway and works through chat apps such as WhatsApp, Telegram, Slack, Discord and iMessage, with a skills system and swappable model plugins. It also ships native apps for macOS, iOS, Android, Windows and Linux. Its README warns that tools run on the host for the main session unless sandboxing is configured, and that inbound messages should be treated as untrusted input.

Pricing: Free and open source (MIT) with no paid tier, hosted service or token; users pay their chosen model providers.

Latest release 2026.10.33:

  • Long conversations and large session stores use bounded export and recovery work, reducing out-of-memory failures during chat, memory export, Doctor repair, and Gateway startup. Authored
  • Interrupted updates recover when their executor dies instead of leaving the Gateway stuck offline, while version-skew checks protect state still used by an installed service. Authored
  • Replies survive more restart and reconnect paths, preserving original prompts, recovering Telegram responses, and avoiding lost WhatsApp replies or skipped Signal messages.
  • Shared-session privacy is stronger: Side chat stays private to its viewer, internal model prompts stay out of displayed output, and compaction redacts credentials in quoted summaries. Authored

Full OpenClaw profile

nanobot vs OpenClaw: common questions

Which is more popular, nanobot or OpenClaw?

OpenClaw has a Gid Score of 71 against 40 for nanobot. The score combines package downloads, editor installs, GitHub activity and attention, updated daily.