Head to head · Proactive personal assistants · October 2026 research run
Caddy vs Leon
Leon scores 41 (E) on agent readiness against Caddy's 16.7 (F), and leads in 6 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 15
Watch for
No API, MCP server or A2A endpoint for an outside agent.
Leon E
Best for A developer who wants a self-hosted assistant with memory, computer use and a local model, and who will read the source.
Ahead on
- Reliability, 32 against 10
- Schema & documentation, 33 against 10
- Agent ergonomics, 57 against 0
- Security & auth, 34 against 0
- Payments & pricing, 60 against 30
- Transparency & trust, 60 against 52
Also in its favour
- No key needed to call it
- Free to start without a card
- Open source
Watch for
No tagged release of the core since 1.0.0-beta.8 on 1 May 2023. The 2.0 Developer Preview is installed by cloning the develop branch
Score by category
| Category | Weight this run | Caddy | Leon | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 10 | 32 | Leon +22 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 10 | 33 | Leon +23 |
| Agent ergonomics | 13%16.2 | 0 | 57 | Leon +57 |
| Security & auth | 14%17.5 | 0 | 34 | Leon +34 |
| Payments & pricing | 10%12.5 | 30 | 60 | Leon +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 55 | 15 | Caddy +40 |
| Transparency & trust | 7%8.8 | 52 | 60 | Leon +8 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 16.7/100 | E 41/100 |
Facts side by side
| Fact | Caddy | Leon |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Caddy Technologies Inc. | Louis Grenard (Leon AI) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Closed service under Caddy's Terms of Service (Caddy Technologies Inc., last updated 27 April 2026). | MIT |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-13 | 2023-05-01 |
| 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 | 18k stars |
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.
Leon
Connected-app credentials are encrypted per profile and the Gmail connection is read-only. The 2.0 Developer Preview has no tagged release, runs tools and a 30-minute proactive pulse with no approval step, listens on every network interface with client authentication off, and sends telemetry by default.
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.
Leon
- Clone the develop branch for 2.0.
npm install --global @leon-ai/cliand docs.getleon.ai install and describe the legacy 1.0 betas - Set
client_interface.auth.enabled: trueand aLEON_PROFILE_TOKENbefore the machine joins a shared network. The server binds 0.0.0.0 - Set
telemetry_enabled: falseandruntime.pulse_enabled: falsein the profileconfig.ymlfor an unattended or private run - Use
availability.tools.allowedto limit tools. Shell, file writes, computer use and browser control are otherwise available to the agent with no approval prompt - Back up
LEON_CONNECTIONS_ENCRYPTION_KEYfrom the profile.env. Without it the stored connections cannot be read
Questions
Which is better for AI agents, Caddy or Leon?
Leon scores 41 (E) on agent readiness against Caddy's 16.7 (F), and leads in 6 of 7 scored categories. Caddy leads on maintenance & community.
Are Caddy and Leon open source?
No open-source release is listed for Caddy. Leon is open source (MIT).
Other comparisons with Caddy or Leon
- asaply vs Caddy
- Asmi vs Caddy
- Boba vs Caddy
- Brea vs Caddy
- Caddy vs Del
- Caddy vs HireAlpha
- Caddy vs OpenInstinct
- Caddy vs Orbits
- Caddy vs Orchid
- Caddy vs szn
- Caddy vs Tab
- Caddy vs Zapia
- AstrBot vs Caddy
- AstrBot vs Leon
- Boski vs Caddy
- Boski vs Leon
- 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 Lindy
- 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 Leon
- folk vs Leon
- GAIA vs Leon
- Gemini Spark vs Leon
- Grok Bot vs Leon
- Haven vs Leon
- Hermes Agent vs Leon
- Instinct vs Leon
- IronClaw vs Leon
- Leon vs Lindy
- Leon vs nanobot
- Leon vs NanoClaw
- Leon vs Dots
- Leon vs OpenClaw
- Leon vs PicoClaw
- Leon vs Poke
- Leon vs QwenPaw
- Leon vs Town
- Leon vs ZeroClaw
- Leon vs Zo Computer
- asaply vs Leon
- Brea vs Leon
- Caddy vs Natura tinyNature
- Caddy vs Pally
- Caddy vs Tomo
- Caddy vs Wajo (Fo)
- Del vs Leon
- HireAlpha vs Leon
- Leon vs Natura tinyNature
- Leon vs Orbits
- Leon vs Orchid
- Leon vs Pally
- Leon vs szn
- Leon vs Tomo
- Leon vs Wajo (Fo)
- Leon vs Zapia
- Asmi vs Leon
- Boba vs Leon
- Caddy vs Talorys
- Leon vs Tab
- Leon vs Talorys
- Leon vs OpenInstinct
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-leon.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/caddy-app.json·/api/v1/tools/leon.json - From a terminal
anchor compare caddy-app leon(the CLI) - Over MCP
compare_tools {"a": "caddy-app", "b": "leon"}at/mcp, no key