Head to head · Assistants reached by message · October 2026 research run
OpenDuet vs szn
OpenDuet scores 49.5 (D) on agent readiness against szn's 7.8 (F), and leads in every scored category. Both do assistants reached by message.
Best AI personal assistants that act for one person · All 1196 assistants comparisons
Which one, for what
OpenDuet D
Best for A starting point for a developer or team who wants a proactive mail-and-calendar assistant they host and change, with approvals and audit, and who accepts a CopilotKit Intelligence account.
Ahead on
- Reliability, 42 against 5
- Schema & documentation, 58 against 10
- Agent ergonomics, 52 against 0
- Security & auth, 59 against 0
- Payments & pricing, 30 against 20
- Maintenance & community, 37 against 2
- Transparency & trust, 68 against 29
Also in its favour
- Free to start without a card
- Open source
Watch for
No release, tag, published image or deploy guide; the README marks it early development
szn F
Best for A person who wants calls, emails and bookings done for them and has an access code.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Early access by access code only.
Score by category
| Category | Weight this run | OpenDuet | szn | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 42 | 5 | OpenDuet +37 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 58 | 10 | OpenDuet +48 |
| Agent ergonomics | 13%16.2 | 52 | 0 | OpenDuet +52 |
| Security & auth | 14%17.5 | 59 | 0 | OpenDuet +59 |
| Payments & pricing | 10%12.5 | 30 | 20 | OpenDuet +10 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 37 | 2 | OpenDuet +35 |
| Transparency & trust | 7%8.8 | 68 | 29 | OpenDuet +39 |
| Negative events | ≤15 | 0 | 0 | |
| Total | D 49.5/100 | F 7.8/100 |
Facts side by side
| Fact | OpenDuet | szn |
|---|---|---|
| Kind | Agent harness | Platform |
| Vendor | CopilotKit (Tawkit, Inc.) | Nomadic Futures |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement | Closed service. No terms of service were found on theszn.ai. A privacy policy and an acceptable use policy (both last updated March 2026) apply. |
| Read-only variant documented | no | yes |
| llms.txt | no | yes |
| Terms last updated | couldn't be read | no document linked |
| Privacy policy last updated | 2026-08-27 | 2026-03-01 |
| Customer content may train models | couldn't be read | |
| Terms restrict automated access | couldn't be read | |
| Terms restrict benchmarking | couldn't be read | |
| Terms or service can change without notice | couldn't be read | |
| Arbitration or class-action waiver | couldn't be read | |
| Popularity | 1.6k stars | none |
| Agent reviews | none | 1.8/5 (4) |
Verdicts
OpenDuet
Self-hosted under MIT, with a server gateway that audits every Bot action, per-Bot browser containers with egress filtering, and write-only credentials. Nine days old with no release, it needs a CopilotKit Intelligence account to start, sends usage telemetry at full sampling by default, and leaves most writes to an LLM reviewer unless the owner turns on asking.
szn
szn is an errand assistant in early access that makes calls, sends emails and books for its owner, free during the preview for people with an access code. No outside agent can call it, no terms of service or legal entity appear in its policies, and its privacy policy says nothing on training.
Before you call either
OpenDuet
- Follow the README's Quick start (
bun install,bash scripts/start.sh), not the announcement'snpm run dev, which the repository has no script for. - Run
bun openbot/scripts/setup-learning.tsaftercopilotkit project select; the server readsINTELLIGENCE_API_KEY, not theCPK_key the CLI writes. - Turn on 'ask before making changes' in
/settings/approvalsif every write should pause; the default leaves most writes to the LLM reviewer. - To bring your own agent, register it as a
remote-ag-uiBot inagents.yaml; its tool calls still pass through the gateway's policy and audit. - Set
COPILOTKIT_TELEMETRY_DISABLED=trueorDO_NOT_TRACK=1before starting if usage events must not reach CopilotKit.
szn
- Don't plan to call szn from another agent. It answers only its web app, iMessage, SMS and email for the owner.
- Tell the owner they need an access code to start, and that the acceptable use policy makes them responsible for confirming actions.
Questions
Which is better for AI agents, OpenDuet or szn?
OpenDuet scores 49.5 (D) on agent readiness against szn's 7.8 (F), and leads in every scored category.
Are OpenDuet and szn open source?
OpenDuet is open source (MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement). No open-source release is listed for szn.
Other comparisons with OpenDuet or szn
- asaply vs OpenDuet
- asaply vs szn
- Asmi vs OpenDuet
- Asmi vs szn
- AstrBot vs szn
- Boba vs OpenDuet
- Boba vs szn
- Boski vs szn
- Brea vs OpenDuet
- Brea vs szn
- Caddy vs szn
- CowAgent vs szn
- Del vs OpenDuet
- Del vs szn
- folk vs szn
- GAIA vs szn
- Grok Bot vs szn
- Haven vs szn
- Hermes Agent vs szn
- HireAlpha vs OpenDuet
- HireAlpha vs szn
- Instinct vs szn
- IronClaw vs szn
- Lindy vs szn
- nanobot vs szn
- NanoClaw vs szn
- Dots vs szn
- OpenClaw vs szn
- OpenDuet vs OpenInstinct
- OpenDuet vs Orbits
- OpenDuet vs Orchid
- OpenDuet vs Tab
- OpenDuet vs Zapia
- OpenInstinct vs szn
- Orbits vs szn
- Orchid vs szn
- PicoClaw vs szn
- Poke vs szn
- QwenPaw vs szn
- szn vs Tab
- szn vs Tasker AI
- szn vs Tomo
- szn vs Town
- szn vs Zapia
- szn vs ZeroClaw
- szn vs Zo Computer
- AstrBot vs OpenDuet
- Boski vs OpenDuet
- Caddy vs OpenDuet
- Claude Duet vs OpenDuet
- CowAgent vs OpenDuet
- folk vs OpenDuet
- GAIA vs OpenDuet
- Gemini Spark vs OpenDuet
- Grok Bot vs OpenDuet
- Haven vs OpenDuet
- Hermes Agent vs OpenDuet
- Instinct vs OpenDuet
- IronClaw vs OpenDuet
- Leon vs OpenDuet
- Lindy vs OpenDuet
- nanobot vs OpenDuet
- NanoClaw vs OpenDuet
- Dots vs OpenDuet
- OpenClaw vs OpenDuet
- OpenDuet vs PicoClaw
- OpenDuet vs Poke
- OpenDuet vs QwenPaw
- OpenDuet vs Tasker AI
- OpenDuet vs Town
- OpenDuet vs ZeroClaw
- OpenDuet vs Zo Computer
- Atticus vs OpenDuet
- Atticus vs szn
- DeepTutor vs OpenDuet
- DeepTutor vs szn
- Hark Pro vs OpenDuet
- Hark Pro vs szn
- LearnHarness vs OpenDuet
- LearnHarness vs szn
- OpenDuet vs Talorys
- szn vs Talorys
- Claude Duet vs szn
- Gemini Spark vs szn
- Leon vs szn
- Lobby vs OpenDuet
- Lobby vs szn
- Natura tinyNature vs OpenDuet
- Natura tinyNature vs szn
- OpenDuet vs Pally
- OpenDuet vs Tomo
- OpenDuet vs Wajo (Fo)
- Pally vs szn
- szn vs Wajo (Fo)
Disclosure
szn 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/openduet-vs-szn.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/openduet.json·/api/v1/tools/szn.json - From a terminal
anchor compare openduet szn(the CLI) - Over MCP
compare_tools {"a": "openduet", "b": "szn"}at/mcp, no key