Head to head · Proactive personal assistants · October 2026 research run
Caddy vs Lindy
Lindy scores 32.3 (F) on agent readiness against Caddy's 16.7 (F), and leads in 5 of 7 scored categories. Caddy leads on maintenance & community. Both do proactive personal assistants.
Best AI personal assistants that act for one person · All 834 assistants comparisons
Which one, for what
Caddy F
Best for People who want a free assistant in iMessage or RCS that watches mail, calendars and work tools and asks before acting.
Ahead on
- Maintenance & community, 55 against 9
Also in its favour
- No incidents deducted, where Lindy loses 3 points for them
Watch for
No API, MCP server or A2A endpoint for an outside agent.
Lindy F
Best for Lindy suits a person or small team that lives in Slack and Google or Microsoft mail and wants briefs, drafts, scheduling and meeting notes done on a schedule.
Ahead on
- Reliability, 24 against 10
- Schema & documentation, 32 against 10
- Agent ergonomics, 43 against 0
- Security & auth, 49 against 0
- Payments & pricing, 35 against 30
Also in its favour
- Free to start without a card
Watch for
The integrations page says approval settings apply in shared Slack threads only. Web chat, Slack direct messages, iMessage and SMS are not covered, and reads are never covered.
Score by category
| Category | Weight this run | Caddy | Lindy | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 10 | 24 | Lindy +14 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 10 | 32 | Lindy +22 |
| Agent ergonomics | 13%16.2 | 0 | 43 | Lindy +43 |
| Security & auth | 14%17.5 | 0 | 49 | Lindy +49 |
| Payments & pricing | 10%12.5 | 30 | 35 | Lindy +5 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 55 | 9 | Caddy +46 |
| Transparency & trust | 7%8.8 | 52 | 52 | even |
| Negative events | ≤15 | 0 | -3 | |
| Total | F 16.7/100 | F 32.3/100 |
Facts side by side
| Fact | Caddy | Lindy |
|---|---|---|
| Kind | Platform | Platform |
| Vendor | Caddy Technologies Inc. | Crivello Corp (doing business as Lindy) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | Closed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026). | Proprietary service under Lindy's Terms of Service. No source is published |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| Last release | 2026-10-13 | 2025-10-21 |
| Terms last updated | 2026-09-24 | |
| Privacy policy last updated | 2026-09-28 | |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | yes | |
| Terms restrict benchmarking | yes | |
| Terms or service can change without notice | yes | |
| Arbitration or class-action waiver | yes |
Verdicts
Caddy
Caddy is a free iMessage and RCS assistant in public beta that watches connected mail, calendars and work apps and asks before sending email or changing data. No outside agent can call it, and no status page, changelog or security contact was found, though its iOS app ships every week or two.
Lindy
Lindy keeps what it remembers in files the owner can read and edit, and publishes credit prices. Its approval setting applies in shared Slack threads only, so writes asked for by direct message, text or web chat run unasked, which its pricing page does not say. It has no status page, and its changelog stops in October 2025.
Before you call either
Caddy
- Don't plan to call Caddy from another agent. It answers the owner's text messages, Siri and group chats it's added to.
- Expect Caddy to ask the owner before it sends email or creates an invite.
Lindy
- Treat a request sent by direct message, text or web chat as unguarded. Approval prompts appear in shared Slack threads only.
- Run a routine as a dry run before turning it on. A dry run reads real data and sends, posts and writes nothing.
- Turn off unused tools after adding an MCP server. Every supported tool arrives switched on, and a large server adds more than a hundred.
- Expect a billed seat for anyone who mentions Lindy in Slack. A teammate who joins that way has seven free days first.
- Connect only hosted MCP servers on public HTTPS with streamable HTTP, the one kind the docs describe.
Questions
Which is better for AI agents, Caddy or Lindy?
Lindy scores 32.3 (F) on agent readiness against Caddy's 16.7 (F), and leads in 5 of 7 scored categories. Caddy leads on maintenance & community.
Other comparisons with Caddy or Lindy
- asaply vs Caddy
- asaply vs Lindy
- Asmi vs Caddy
- Asmi vs Lindy
- Boba vs Caddy
- Boba vs Lindy
- Brea vs Caddy
- Brea vs Lindy
- Caddy vs Del
- Caddy vs HireAlpha
- Caddy vs OpenInstinct
- Caddy vs Orbits
- Caddy vs Orchid
- Caddy vs szn
- Caddy vs Tab
- Caddy vs Zapia
- Del vs Lindy
- HireAlpha vs Lindy
- Lindy vs OpenInstinct
- Lindy vs Orbits
- Lindy vs Orchid
- Lindy vs szn
- Lindy vs Tab
- Lindy vs Zapia
- AstrBot vs Caddy
- AstrBot vs Lindy
- Boski vs Caddy
- Boski vs Lindy
- Caddy vs CowAgent
- Caddy vs folk
- Caddy vs GAIA
- Caddy vs Gemini Spark
- Caddy vs Grok Bot
- Caddy vs Haven
- Caddy vs Hermes Agent
- Caddy vs Instinct
- Caddy vs IronClaw
- Caddy vs Leon
- Caddy vs nanobot
- Caddy vs NanoClaw
- Caddy vs Dots
- Caddy vs OpenClaw
- Caddy vs PicoClaw
- Caddy vs Poke
- Caddy vs QwenPaw
- Caddy vs Town
- Caddy vs ZeroClaw
- Caddy vs Zo Computer
- CowAgent vs Lindy
- folk vs Lindy
- GAIA vs Lindy
- Gemini Spark vs Lindy
- Grok Bot vs Lindy
- Haven vs Lindy
- Hermes Agent vs Lindy
- Instinct vs Lindy
- IronClaw vs Lindy
- Leon vs Lindy
- Lindy vs nanobot
- Lindy vs NanoClaw
- Lindy vs Dots
- Lindy vs OpenClaw
- Lindy vs PicoClaw
- Lindy vs Poke
- Lindy vs QwenPaw
- Lindy vs Town
- Lindy vs ZeroClaw
- Lindy vs Zo Computer
- Caddy vs Natura tinyNature
- Caddy vs Pally
- Caddy vs Tomo
- Caddy vs Wajo (Fo)
- Lindy vs Natura tinyNature
- Lindy vs Pally
- Lindy vs Tomo
- Lindy vs Wajo (Fo)
- Caddy vs Talorys
- Lindy vs Talorys
Disclosure
Caddy 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/caddy-app-vs-lindy.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/caddy-app.json·/api/v1/tools/lindy.json - From a terminal
anchor compare caddy-app lindy(the CLI) - Over MCP
compare_tools {"a": "caddy-app", "b": "lindy"}at/mcp, no key