Head to head · Assistants reached by message · October 2026 research run
Orbits vs ZeroClaw
ZeroClaw scores 70.2 (BB) on agent readiness against Orbits's 15.6 (F), and leads in every scored category. Both do assistants reached by message.
Best AI personal assistants that act for one person · All 834 assistants comparisons
Which one, for what
Orbits F
Best for Families who want one shared assistant for calendars, lists, meals, chores and household email.
Also in its favour
- No incidents deducted, where ZeroClaw loses 3 points for them
Watch for
No public agent API, as llms.txt states.
ZeroClaw BB
Best for One person who wants an assistant on their own hardware that answers on Telegram, Discord, Matrix or email, asks before it writes or runs commands, and works with a local model.
Ahead on
- Reliability, 74 against 15
- Schema & documentation, 82 against 10
- Agent ergonomics, 72 against 0
- Security & auth, 76 against 0
- Payments & pricing, 60 against 20
- Maintenance & community, 80 against 54
- Transparency & trust, 64 against 43
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- Free to start without a card
- Open source
Watch for
The docs state that command execution is not audited. [security.audit] records certificate events only, and tool receipts are opt-in and not durable
Score by category
| Category | Weight this run | Orbits | ZeroClaw | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 15 | 74 | ZeroClaw +59 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 10 | 82 | ZeroClaw +72 |
| Agent ergonomics | 13%16.2 | 0 | 72 | ZeroClaw +72 |
| Security & auth | 14%17.5 | 0 | 76 | ZeroClaw +76 |
| Payments & pricing | 10%12.5 | 20 | 60 | ZeroClaw +40 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 54 | 80 | ZeroClaw +26 |
| Transparency & trust | 7%8.8 | 43 | 64 | ZeroClaw +21 |
| Negative events | ≤15 | 0 | -3 | |
| Total | F 15.6/100 | BB 70.2/100 |
Facts side by side
| Fact | Orbits | ZeroClaw |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Nemus AI, Inc. | ZeroClaw Labs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Closed service under the Orbits Terms of Service (Nemus AI, Inc.). | MIT OR Apache-2.0 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-13 | 2026-09-05 |
| Terms last updated | no document linked | |
| Privacy policy last updated | no document linked | |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | none | 33k stars |
Verdicts
Orbits
Orbits is a family household app whose assistant, Bit, runs shared calendars, lists and meals, reads household email and places restaurant calls after approval, with iOS releases every week or two. No outside agent can call it, prices appear only as App Store in-app purchases, and no status page, security contact or named subprocessors were found.
ZeroClaw
Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.
Before you call either
Orbits
- Don't plan to call Orbits from another agent. llms.txt says no public agent API is offered.
- Tell the owner the assistant needs an Orbits subscription bought in the app, and that any trial appears only at purchase.
ZeroClaw
- Keep
[risk_profiles.<alias>] level = "supervised".fullruns every tool not listed inalways_ask, and the YOLO preset removes the sandbox and path rules too - Add sending and account tools such as
send_via,google_workspaceandhttp_requesttoalways_askso a session-level Always grant cannot skip the prompt - List senders in
[peer_groups.<name>] external_peers.["*"]accepts anyone on that channel - Set
[web_fetch].allowed_domainsand[http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress - Run one-shot tasks with
zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy
Questions
Which is better for AI agents, Orbits or ZeroClaw?
ZeroClaw scores 70.2 (BB) on agent readiness against Orbits's 15.6 (F), and leads in every scored category.
Are Orbits and ZeroClaw open source?
No open-source release is listed for Orbits. ZeroClaw is open source (MIT OR Apache-2.0).
Other comparisons with Orbits or ZeroClaw
- asaply vs Orbits
- asaply vs ZeroClaw
- Asmi vs Orbits
- Asmi vs ZeroClaw
- AstrBot vs Orbits
- Boba vs Orbits
- Boba vs ZeroClaw
- Boski vs Orbits
- Brea vs Orbits
- Brea vs ZeroClaw
- Caddy vs Orbits
- CowAgent vs Orbits
- Del vs Orbits
- Del vs ZeroClaw
- folk vs Orbits
- GAIA vs Orbits
- Grok Bot vs Orbits
- Haven vs Orbits
- Hermes Agent vs Orbits
- HireAlpha vs Orbits
- HireAlpha vs ZeroClaw
- Instinct vs Orbits
- IronClaw vs Orbits
- Lindy vs Orbits
- nanobot vs Orbits
- NanoClaw vs Orbits
- Dots vs Orbits
- OpenClaw vs Orbits
- OpenInstinct vs Orbits
- OpenInstinct vs ZeroClaw
- Orbits vs Orchid
- Orbits vs Pally
- Orbits vs PicoClaw
- Orbits vs Poke
- Orbits vs QwenPaw
- Orbits vs szn
- Orbits vs Tab
- Orbits vs Tomo
- Orbits vs Town
- Orbits vs Zapia
- Orbits vs Zo Computer
- Orchid vs ZeroClaw
- szn vs ZeroClaw
- Tab vs ZeroClaw
- Zapia vs ZeroClaw
- AstrBot vs ZeroClaw
- Boski vs ZeroClaw
- Caddy vs ZeroClaw
- CowAgent vs ZeroClaw
- folk vs ZeroClaw
- GAIA vs ZeroClaw
- Gemini Spark vs ZeroClaw
- Grok Bot vs ZeroClaw
- Haven vs ZeroClaw
- Hermes Agent vs ZeroClaw
- Instinct vs ZeroClaw
- IronClaw vs ZeroClaw
- Leon vs ZeroClaw
- Lindy vs ZeroClaw
- nanobot vs ZeroClaw
- NanoClaw vs ZeroClaw
- Dots vs ZeroClaw
- OpenClaw vs ZeroClaw
- PicoClaw vs ZeroClaw
- Poke vs ZeroClaw
- QwenPaw vs ZeroClaw
- Town vs ZeroClaw
- ZeroClaw vs Zo Computer
- Gemini Spark vs Orbits
- Leon vs Orbits
- Natura tinyNature vs Orbits
- Natura tinyNature vs ZeroClaw
- Orbits vs Wajo (Fo)
- Pally vs ZeroClaw
- Tomo vs ZeroClaw
- Wajo (Fo) vs ZeroClaw
- Orbits vs Talorys
- Talorys vs ZeroClaw
Disclosure
Orbits competes with LocalGhost, which Anchor Terminal's founder builds. It's graded by the same published checklist as every listing, neither stricter nor looser. Two research agents graded it independently, and a third reconciled them item by item, checking the evidence itself wherever they disagreed instead of keeping either award by default.
Machine-readable
- This page as Markdown
/compare/orbits-vs-zeroclaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/orbits.json·/api/v1/tools/zeroclaw.json - From a terminal
anchor compare orbits zeroclaw(the CLI) - Over MCP
compare_tools {"a": "orbits", "b": "zeroclaw"}at/mcp, no key