- The desktop starts again when you are signed in. The loopback door now asks for the port it had last, so the provider row is usually right as it is.
- The relay's console loads on a large record. The relay keeps the figures of a turn run on a key of the person's own in one small row…
- A task can be given a budget: tokens, money, time, and the size of one request. Off unless set.
- Recall searches the whole memory store. Keyword search and recall by meaning read every memory, not only the newest 1,000 the listing shows, and a near-duplicate is found anywhere in the store…
- A contact's card folds its long lines at 75 octets. render_vcard wrote a long Chinese note as one oversized line, past what RFC 6350 allows, so a strict importer could reject or truncate it.
- TestFlight. Build 31 (1.0.8) was uploaded this morning and handed to the external group nanoMuse Beta for Apple's beta review; 1.0.9 goes up as build 32 to the same group and review.
nanoMuse
nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.
Recently added on Nov 19, 2026. The description, category and pricing were filled in from public metadata and have not been checked by an editor yet.
On this page
Usage data: latest readings Nov 18 to Nov 19, 2026, last checked Nov 19, 08:19 UTC. Date of each number
What nanoMuse does
It is free and open source (GPL-3.0); you pay only for the models it calls.
Key facts
| Maker | nanoMuse |
|---|---|
| First released | September 2026 |
| License | GPL-3.0 |
| Main language | Swift |
| Open issues and PRs | 172 |
Pricing
Open source under the GPL-3.0 licence; check the website for any paid hosted plans.
Checked Nov 19, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (GPL-3.0)
- Closest alternativeOpenClaw · all alternatives
nanoMuse alternatives
Best nanoMuse alternatives compared · All general-purpose AI agents
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 8 |
OpenClawOpenClaw Foundation (nonprofit); created by Peter Steinberger |
71 | 3.1M | up 5.8% | down 24.3% | 395K+120/day | 2026.10.332d ago | Free (OSS) | |||
| 10 |
DeepSeek HarnessDeepSeek |
67 | 658K | down 22.5% | up 59.3% | 284K+685/day | — | Free | |||
| 13 |
Hermes AgentNous Research |
63 | 88.2K | up 34.8% | — | 265K+293/day | 0.23.24d ago | Free (OSS) | |||
| 39 |
ManusButterfly Effect Pte. Ltd. (Manus AI), Singapore |
51 | — | — | — | — | — | $20/mo | |||
| 56 |
Cloudflare OSCloudflare |
46 | — | — | — | 11.8K+10/day | — | Free (OSS) | |||
| 59 |
|
462/4 | — | — | — | — | — | Free | |||
Ratings from people who use nanoMuse
No ratings yet. Used nanoMuse? Rate it and say what it is good and bad at.
nanoMuse news
-
7 agents added to AgentGid
Billion Context, ARTEX, Meldwork, Theia, nanoMuse, OhMyGame, Poki
What changed: recent nanoMuse releases
50 stable releases in the last 90 days · Full changelog
- A scheduled task's cards reach your phone, and the first answer decides. A scheduled run on nanoMuse Desktop asks while nobody may be at the computer.
- Every device reads what the others are doing. A turn used to tell the account's other devices only that it started and that it ended.
- The wait before the first token is spoken of, and the prompts are smaller. The relay lets twelve requests reach the model at once and held the rest in silence.
- The record says who started each call, and what you thought of the reply. Every chat request and every own-key turn sent up carries who started it…
- The operator reads the record question by question, and the figures read an index. One message often takes the agent several model calls, and the record counted each as a turn.
- The runtime, on Windows and elsewhere. A private file (the settings, the vault, the channel tokens, the ChatGPT token, the calendar and contacts caches) stays its owner's alone on Windows, where…
Earlier releases
- The record: every conversation, on every device, whichever key answered. nanoMuse Cloud keeps each chat turn it answered since relay 0.29, in full, with the pictures as files named by their…
- The face's clips travel with the face, and each device says what answers it. A clip drawn on one device is put up and named in the profile's clips ({mood: {sha256, mime, bytes}}).
- nanoMuse Cloud answers the nanoMuse apps only. A sixth switch on the operator's Controls, nanoMuse clients only, is on by default: a chat request on an account key from software that is not one of…
- The operator's console is rebuilt, and the relay reads off the requests' path. /app/admin is a small React application (cloud/console, built into the relay package and checked by CI), in 简体中文 and…
- The runtime, in detail. A thinking model's reasoning shows while it thinks, in the console and the web console's bubble, not only after the answer,
- The desktop. A device on the hub can no longer stop a task or decide an approval card belonging to another device,
- nanoMuse Cloud is one model, for chat and for the screen. The account serves Qwen/Qwen3.6-27B-FP8, a multimodal model that reads pictures, so the chat and the hands run on the same deployment.
- Pictures and clips come from a provider of your own. nanoMuse Cloud stopped funding image and video generation: the Making pictures and Making clips rows on Android, the iPhone, the desktop and…
- The relay's sign-in gives nothing away, and a credential is one device. A wrong password, an unknown account and an account without a password get the same answer.
- The runtime finishes what it started. A reminder, routine, goal pass, check-in or trigger that the runtime did not get to finish is written to a small outbox before it joins the chat's queue and…
- An approval relayed to another device is remembered for that step alone. When the computer asks the phone whether a command may run and you answer always, the phone used to remember the answer by…
- The desktop, in detail. Restarting the Host (Restart now under the proxy row, and the restart macOS asks for after a Screen Recording grant) lists a reply, the hands, a task from another device or…
- The daily feed is written quietly, and a routine speaks first. On Android, the iPhone and the desktop the conversation the feed is written in no longer appears in the drawer, the chat list or…
- The Android approval card fits the screen, and the ChatGPT sign-in has a way through a proxy.
- The iPhone, in detail. The conversation scrolls under the header and fades into its scrim, as it does under the composer, and on an iPad the agent's replies line up with the composer.
- The desktop does what its buttons say. Default face, the clip preview's Cancel, Media's Check which models answer, the ChatGPT Open the sign-in page, Sign out and Cancel, and Download and Reset…
- The Windows release carries the files an in-app update needs. Beside the installer, the release has latest.yml, which names the installer and its SHA-512, and the installer's .exe.blockmap…
- DeepSeek Harness on the runtime, and one address per endpoint. A computer running nanomuse serve lists the chats of dsh web and DeepSeek's desktop app under ~/.dsh beside Cursor, Codex and Claude…
- The iPad's chat is one column, and the pill bar is glass again. On an iPad the messages, the composer and the pill bar share one centred column of 760 pt, the web console's width.
- Your devices agree with each other. Signing in on an iPhone brings the account's chats, name and face down at once, instead of after a trip to the background.
- A step another device's Muse asks about is answered on the iPhone. A task sent with @〈device〉 runs on that device's Muse.
- DeepSeek Harness is a fourth coding agent. The Coding agents page on the desktop, and from the phone over the hub, knew Cursor, Codex and Claude Code.
- A web search that needs no key. provider = "you" under [connectors.search], or the You.com chip under Connections → Web search, searches You.com without an account, 100 times a day per address.
- Secrets where they belong. An MCP server's env values typed in the app went into app-settings.json as plain text.
nanoMuse popularity and usage data
The GitHub repository has 3,591 stars, 2,067 of them added in the last 30 days. The latest stable release is 1.0.9, published Oct 29, 2026; there were 4 stable releases in the past 30 days.
Download the raw daily series: nanomuse.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| GitHub stars | Nov 19, 2026 | Nov 19, 08:19 UTC |
| Website rank (Tranco) | Nov 18, 2026 | Nov 19, 08:19 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
nanoMuse FAQ
How much does nanoMuse cost?
Open source under the GPL-3.0 licence; check the website for any paid hosted plans.
Is nanoMuse open source?
Yes. nanoMuse is open source, released under the GPL-3.0 license.
How popular is nanoMuse?
The GitHub repository has 3,591 stars, 2,067 of them added in the last 30 days. The latest stable release is 1.0.9, published Oct 29, 2026; there were 4 stable releases in the past 30 days.
What is the latest version of nanoMuse?
The latest stable release we track is 1.0.9, published on Oct 29, 2026.
What are the alternatives to nanoMuse?
The closest alternatives in the same category by Gid Score are OpenClaw, DeepSeek Harness, Hermes Agent, Manus.
For the makers of nanoMuse badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/nanomuse/)
[](https://agentgid.com/agents/nanomuse/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
GitHub: nano-muse/nanomuse. Site rank: nanomuse.cn on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: nanomuse.cn, github.com.