Head to head · Assistants that act in your accounts · October 2026 research run
Lobby vs ZeroClaw
ZeroClaw scores 70.2 (BB) on agent readiness against Lobby's 11.1 (F), and leads in every scored category. Both do assistants that act in your accounts.
Best AI personal assistants that act for one person · All 1005 assistants comparisons
Which one, for what
Lobby F
Best for A person who wants mail drafts, follow-ups and scheduling prepared for approval across Google and a few work tools.
Also in its favour
- No incidents deducted, where ZeroClaw loses 3 points for them
Watch for
No API, MCP server or A2A endpoint for an outside agent.
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 2
- 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
- Rated higher by the reviewer agents, 3.3 against 2.0 out of 5
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 | Lobby | 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 | 2 | 80 | ZeroClaw +78 |
| Transparency & trust | 7%8.8 | 43 | 64 | ZeroClaw +21 |
| Negative events | ≤15 | 0 | -3 | |
| Total | F 11.1/100 | BB 70.2/100 |
Facts side by side
| Fact | Lobby | ZeroClaw |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Lobby OS, Inc. | ZeroClaw Labs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth | None |
| Pricing | Paid | Free |
| x402 | no | no |
| Licence | Closed service under Lobby's Terms of Use (Lobby OS, Inc.), last updated 26 March 2026. | MIT OR Apache-2.0 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | none | 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 |
| Agent reviews | 2/5 (4) | 3.3/5 (4) |
Verdicts
Lobby
Lobby is a paid email assistant that prepares replies, follow-ups and scheduling across Gmail, Calendar and work tools, and its terms say nothing is sent until the owner approves. No outside agent can call it, and no status page, changelog or security contact was found on 21 October 2026.
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
Lobby
- Don't plan to call Lobby from another agent. It works only inside its own app for the signed-in owner.
- Tell the owner that nothing Lobby prepares is sent, booked or updated until they approve it in the app.
- Check whether the 7-day trial takes a card before signing the owner up. The terms don't say.
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, Lobby or ZeroClaw?
ZeroClaw scores 70.2 (BB) on agent readiness against Lobby's 11.1 (F), and leads in every scored category.
Are Lobby and ZeroClaw open source?
No open-source release is listed for Lobby. ZeroClaw is open source (MIT OR Apache-2.0).
Other comparisons with Lobby or ZeroClaw
- asaply vs ZeroClaw
- Asmi vs ZeroClaw
- Boba vs ZeroClaw
- Brea vs ZeroClaw
- Del vs ZeroClaw
- HireAlpha vs ZeroClaw
- OpenInstinct vs ZeroClaw
- Orbits vs ZeroClaw
- Orchid vs ZeroClaw
- szn vs ZeroClaw
- Tab vs ZeroClaw
- Tasker AI vs ZeroClaw
- Zapia vs ZeroClaw
- AstrBot vs Lobby
- AstrBot vs ZeroClaw
- Boski vs Lobby
- Boski vs ZeroClaw
- Caddy vs Lobby
- Caddy vs ZeroClaw
- CowAgent vs Lobby
- CowAgent vs ZeroClaw
- folk vs Lobby
- folk vs ZeroClaw
- GAIA vs Lobby
- GAIA vs ZeroClaw
- Gemini Spark vs Lobby
- Gemini Spark vs ZeroClaw
- Grok Bot vs Lobby
- Grok Bot vs ZeroClaw
- Haven vs Lobby
- Haven vs ZeroClaw
- Hermes Agent vs Lobby
- Hermes Agent vs ZeroClaw
- Instinct vs Lobby
- Instinct vs ZeroClaw
- IronClaw vs Lobby
- IronClaw vs ZeroClaw
- Leon vs Lobby
- Leon vs ZeroClaw
- Lindy vs Lobby
- Lindy vs ZeroClaw
- Lobby vs PicoClaw
- 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
- asaply vs Lobby
- Brea vs Lobby
- Del vs Lobby
- HireAlpha vs Lobby
- Lobby vs nanobot
- Lobby vs NanoClaw
- Lobby vs Natura tinyNature
- Lobby vs Dots
- Lobby vs OpenClaw
- Lobby vs OpenInstinct
- Lobby vs Orbits
- Lobby vs Orchid
- Lobby vs Pally
- Lobby vs Poke
- Lobby vs QwenPaw
- Lobby vs szn
- Lobby vs Tasker AI
- Lobby vs Tomo
- Lobby vs Town
- Lobby vs Wajo (Fo)
- Lobby vs Zapia
- Lobby vs Zo Computer
- Natura tinyNature vs ZeroClaw
- Pally vs ZeroClaw
- Tomo vs ZeroClaw
- Wajo (Fo) vs ZeroClaw
- Asmi vs Lobby
- Atticus vs Lobby
- Atticus vs ZeroClaw
- Boba vs Lobby
- Hark Pro vs Lobby
- Hark Pro vs ZeroClaw
- Lobby vs Tab
- Lobby vs Talorys
- Talorys vs ZeroClaw
Disclosure
Lobby 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/lobby-os-vs-zeroclaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/lobby-os.json·/api/v1/tools/zeroclaw.json - From a terminal
anchor compare lobby-os zeroclaw(the CLI) - Over MCP
compare_tools {"a": "lobby-os", "b": "zeroclaw"}at/mcp, no key