Head to head · Proactive personal assistants · October 2026 research run
Town vs ZeroClaw
ZeroClaw scores 70.2 (BB) on agent readiness against Town's 48.7 (D), and leads in 6 of 7 scored categories. Both do proactive personal assistants.
Best AI personal assistants that act for one person · All 834 assistants comparisons
Which one, for what
Town D
Best for An owner who wants a mail and calendar assistant whose routines other systems can trigger.
Also in its favour
- No incidents deducted, where ZeroClaw loses 3 points for them
Watch for
The privacy policy describes training with an opt-out and the trust page says training is opt-in.
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 35
- Schema & documentation, 82 against 33
- Agent ergonomics, 72 against 49
- Payments & pricing, 60 against 30
- Maintenance & community, 80 against 60
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- 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 | Town | ZeroClaw | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 35 | 74 | ZeroClaw +39 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 33 | 82 | ZeroClaw +49 |
| Agent ergonomics | 13%16.2 | 49 | 72 | ZeroClaw +23 |
| Security & auth | 14%17.5 | 79 | 76 | Town +3 |
| Payments & pricing | 10%12.5 | 30 | 60 | ZeroClaw +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 60 | 80 | ZeroClaw +20 |
| Transparency & trust | 7%8.8 | 63 | 64 | ZeroClaw +1 |
| Negative events | ≤15 | 0 | -3 | |
| Total | D 48.7/100 | BB 70.2/100 |
Facts side by side
| Fact | Town | ZeroClaw |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Town.com, Inc. | ZeroClaw Labs |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | HTTP | |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | Closed service under Town's Terms of Service (Town.com, Inc., updated 21 July 2026). | MIT OR Apache-2.0 |
| Read-only variant documented | yes | yes |
| llms.txt | no | yes |
| Last release | 2026-10-10 | 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
Town
Town is a hosted assistant that works across the owner's mail, calendar and work apps, and other systems can start its routines through per-routine webhooks with rotatable secrets, idempotency keys and documented errors. A caller can't read a run's result. The privacy policy and trust page disagree on whether training is on by default.
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
Town
- Start a Town routine with POST to its webhook URL, Authorization Bearer whsec_ secret, and application/json or text/plain. Expect 202 only.
- Send X-Town-Idempotency-Key with a stable event id on every retry so Town doesn't start a second run.
- Treat 404 as wrong secret, disabled endpoint or missing endpoint alike, and ask the owner to check Routine Settings rather than retrying.
- Send account_email only if the owner allowed the override. It must match a connected account in full and can't widen the routine's scope.
- Ask the owner to keep routines that act on webhook input in approval-required mode, as Town's own docs advise.
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, Town or ZeroClaw?
ZeroClaw scores 70.2 (BB) on agent readiness against Town's 48.7 (D), and leads in 6 of 7 scored categories.
Are Town and ZeroClaw open source?
No open-source release is listed for Town. ZeroClaw is open source (MIT OR Apache-2.0).
Other comparisons with Town or ZeroClaw
- asaply vs Town
- asaply vs ZeroClaw
- Asmi vs Town
- Asmi vs ZeroClaw
- Boba vs Town
- Boba vs ZeroClaw
- Brea vs Town
- Brea vs ZeroClaw
- Del vs Town
- Del vs ZeroClaw
- HireAlpha vs Town
- HireAlpha vs ZeroClaw
- OpenInstinct vs Town
- OpenInstinct vs ZeroClaw
- Orbits vs Town
- Orbits vs ZeroClaw
- Orchid vs Town
- Orchid vs ZeroClaw
- szn vs Town
- szn vs ZeroClaw
- Tab vs Town
- Tab vs ZeroClaw
- Town vs Zapia
- Zapia vs ZeroClaw
- AstrBot vs Town
- AstrBot vs ZeroClaw
- Boski vs Town
- Boski vs ZeroClaw
- Caddy vs Town
- Caddy vs ZeroClaw
- CowAgent vs Town
- CowAgent vs ZeroClaw
- folk vs Town
- folk vs ZeroClaw
- GAIA vs Town
- GAIA vs ZeroClaw
- Gemini Spark vs Town
- Gemini Spark vs ZeroClaw
- Grok Bot vs Town
- Grok Bot vs ZeroClaw
- Haven vs Town
- Haven vs ZeroClaw
- Hermes Agent vs Town
- Hermes Agent vs ZeroClaw
- Instinct vs Town
- Instinct vs ZeroClaw
- IronClaw vs Town
- IronClaw vs ZeroClaw
- Leon vs Town
- Leon vs ZeroClaw
- Lindy vs Town
- Lindy vs ZeroClaw
- nanobot vs Town
- nanobot vs ZeroClaw
- NanoClaw vs Town
- NanoClaw vs ZeroClaw
- Dots vs Town
- Dots vs ZeroClaw
- OpenClaw vs Town
- OpenClaw vs ZeroClaw
- PicoClaw vs Town
- PicoClaw vs ZeroClaw
- Poke vs Town
- Poke vs ZeroClaw
- QwenPaw vs Town
- QwenPaw vs ZeroClaw
- Town vs Zo Computer
- ZeroClaw vs Zo Computer
- Natura tinyNature vs Town
- Natura tinyNature vs ZeroClaw
- Pally vs Town
- Pally vs ZeroClaw
- Tomo vs Town
- Tomo vs ZeroClaw
- Town vs Wajo (Fo)
- Wajo (Fo) vs ZeroClaw
- Talorys vs Town
- Talorys vs ZeroClaw
Disclosure
Town 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/town-vs-zeroclaw.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/town.json·/api/v1/tools/zeroclaw.json - From a terminal
anchor compare town zeroclaw(the CLI) - Over MCP
compare_tools {"a": "town", "b": "zeroclaw"}at/mcp, no key