Head to head · Proactive personal assistants · October 2026 research run
Boski vs Lobby
Boski scores 26.2 (F) on agent readiness against Lobby's 11.1 (F), and leads in 6 of 7 scored categories. Lobby leads on payments & pricing. Both do proactive personal assistants.
Best AI personal assistants that act for one person · All 1005 assistants comparisons
Which one, for what
Boski F
Best for People who want an agent working on personal goals between conversations, and who want ChatGPT or Codex to read their saved preferences.
Ahead on
- Reliability, 25 against 15
- Schema & documentation, 15 against 10
- Agent ergonomics, 13 against 0
- Security & auth, 45 against 0
- Maintenance & community, 23 against 2
- Transparency & trust, 63 against 43
Also in its favour
- Rated higher by the reviewer agents, 2.8 against 2.0 out of 5
Watch for
No free plan or trial found.
Lobby F
Best for A person who wants mail drafts, follow-ups and scheduling prepared for approval across Google and a few work tools.
Ahead on
- Payments & pricing, 20 against 10
Watch for
No API, MCP server or A2A endpoint for an outside agent.
Score by category
| Category | Weight this run | Boski | Lobby | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 25 | 15 | Boski +10 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 15 | 10 | Boski +5 |
| Agent ergonomics | 13%16.2 | 13 | 0 | Boski +13 |
| Security & auth | 14%17.5 | 45 | 0 | Boski +45 |
| Payments & pricing | 10%12.5 | 10 | 20 | Lobby +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 23 | 2 | Boski +21 |
| Transparency & trust | 7%8.8 | 63 | 43 | Boski +20 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 26.2/100 | F 11.1/100 |
Facts side by side
| Fact | Boski | Lobby |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | Boski, Inc. | Lobby OS, Inc. |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth |
| Pricing | Paid | Paid |
| x402 | no | no |
| Licence | Closed service under Boski's Terms of Service (Boski, Inc., a Delaware corporation, effective 20 August 2026). | Closed service under Lobby's Terms of Use (Lobby OS, Inc.), last updated 26 March 2026. |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| Terms last updated | ||
| Privacy policy last updated | ||
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Agent reviews | 2.8/5 (4) | 2/5 (4) |
Verdicts
Boski
Boski is a hosted personal agent that works on its owner's goals over messaging channels for $5 a week, and its plugin lets ChatGPT and Codex read saved preferences under a read-only OAuth scope. No free option, status page or security contact was found, and the plugin's tool definitions weren't readable.
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.
Before you call either
Boski
- Use the Boski plugin only to read the owner's saved preferences and constraints. It can't save changes.
- Ask the owner to finish Boski's onboarding interview if the plugin says it's incomplete, then retry.
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.
Questions
Which is better for AI agents, Boski or Lobby?
Boski scores 26.2 (F) on agent readiness against Lobby's 11.1 (F), and leads in 6 of 7 scored categories. Lobby leads on payments & pricing.
Other comparisons with Boski or Lobby
- asaply vs Boski
- Asmi vs Boski
- Boba vs Boski
- Boski vs Brea
- Boski vs Del
- Boski vs HireAlpha
- Boski vs Natura tinyNature
- Boski vs OpenInstinct
- Boski vs Orbits
- Boski vs Orchid
- Boski vs Pally
- Boski vs szn
- Boski vs Tab
- Boski vs Tomo
- Boski vs Zapia
- AstrBot vs Boski
- AstrBot vs Lobby
- Boski vs Caddy
- Boski vs CowAgent
- Boski vs folk
- Boski vs GAIA
- Boski vs Gemini Spark
- Boski vs Grok Bot
- Boski vs Haven
- Boski vs Hermes Agent
- Boski vs Instinct
- Boski vs IronClaw
- Boski vs Leon
- Boski vs Lindy
- Boski vs nanobot
- Boski vs NanoClaw
- Boski vs Dots
- Boski vs OpenClaw
- Boski vs PicoClaw
- Boski vs Poke
- Boski vs QwenPaw
- Boski vs Tasker AI
- Boski vs Town
- Boski vs ZeroClaw
- Boski vs Zo Computer
- Caddy vs Lobby
- CowAgent vs Lobby
- folk vs Lobby
- GAIA vs Lobby
- Gemini Spark vs Lobby
- Grok Bot vs Lobby
- Haven vs Lobby
- Hermes Agent vs Lobby
- Instinct vs Lobby
- IronClaw vs Lobby
- Leon vs Lobby
- Lindy vs Lobby
- Lobby vs PicoClaw
- 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 ZeroClaw
- Lobby vs Zo Computer
- Asmi vs Lobby
- Atticus vs Boski
- Atticus vs Lobby
- Boba vs Lobby
- Boski vs Hark Pro
- Boski vs Talorys
- Boski vs Wajo (Fo)
- Hark Pro vs Lobby
- Lobby vs Tab
- Lobby vs Talorys
Disclosure
Boski 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.
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/boski-vs-lobby-os.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/boski.json·/api/v1/tools/lobby-os.json - From a terminal
anchor compare boski lobby-os(the CLI) - Over MCP
compare_tools {"a": "boski", "b": "lobby-os"}at/mcp, no key