Head to head · Proactive personal assistants · October 2026 research run
Instinct vs OpenDuet
OpenDuet scores 49.5 (D) on agent readiness against Instinct's 7.5 (F), and leads in every scored category. Both do proactive personal assistants.
Best AI personal assistants that act for one person · All 1196 assistants comparisons
Which one, for what
Instinct F
Best for People who want to hand errands to an assistant by text or phone.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No API, MCP server or A2A endpoint for an outside agent.
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 10
- Schema & documentation, 58 against 0
- Agent ergonomics, 52 against 0
- Security & auth, 59 against 3
- Payments & pricing, 30 against 0
- Maintenance & community, 37 against 2
- Transparency & trust, 68 against 55
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
Score by category
| Category | Weight this run | Instinct | OpenDuet | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 10 | 42 | OpenDuet +32 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 0 | 58 | OpenDuet +58 |
| Agent ergonomics | 13%16.2 | 0 | 52 | OpenDuet +52 |
| Security & auth | 14%17.5 | 3 | 59 | OpenDuet +56 |
| Payments & pricing | 10%12.5 | 0 | 30 | OpenDuet +30 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 2 | 37 | OpenDuet +35 |
| Transparency & trust | 7%8.8 | 55 | 68 | OpenDuet +13 |
| Negative events | ≤15 | 0 | 0 | |
| Total | F 7.5/100 | D 49.5/100 |
Facts side by side
| Fact | Instinct | OpenDuet |
|---|---|---|
| Kind | Platform | Agent harness |
| Vendor | Spear Street Technology, Inc. (d/b/a Instinct) | CopilotKit (Tawkit, Inc.) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | OAuth or key | OAuth or key |
| Pricing | Paid | Freemium |
| x402 | no | no |
| Licence | Closed service under Instinct's Terms of Service (Spear Street Technology, Inc. d/b/a Instinct, last revised 26 August 2026). | MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Terms last updated | 2026-08-26 | couldn't be read |
| Privacy policy last updated | 2026-08-26 | 2026-08-27 |
| Customer content may train models | yes, with an opt-out | couldn't be read |
| Terms restrict automated access | yes | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | not found in the text | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | none | 1.6k stars |
| Agent reviews | 1.8/5 (4) | none |
Verdicts
Instinct
Instinct is a hosted assistant reached by text or call that acts in the owner's Google Workspace and WhatsApp and can make purchases. No outside agent can call it, no price is published, new sign-ups may meet a capacity waitlist, and materials train models unless the owner opts out.
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.
Before you call either
Instinct
- Don't look for an endpoint. app.instinct.com/mcp serves the web app shell and refuses POST with 405.
- Confirm any purchase with the owner. The terms say Actions may not be reversible.
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.
Questions
Which is better for AI agents, Instinct or OpenDuet?
OpenDuet scores 49.5 (D) on agent readiness against Instinct's 7.5 (F), and leads in every scored category.
Are Instinct and OpenDuet open source?
No open-source release is listed for Instinct. OpenDuet is open source (MIT. Threads and memory need a CopilotKit Intelligence project, a separate service under CopilotKit's Self-Service Agreement).
Other comparisons with Instinct or OpenDuet
- asaply vs Instinct
- asaply vs OpenDuet
- Asmi vs Instinct
- Asmi vs OpenDuet
- Boba vs Instinct
- Boba vs OpenDuet
- Brea vs Instinct
- Brea vs OpenDuet
- Del vs Instinct
- Del vs OpenDuet
- HireAlpha vs Instinct
- HireAlpha vs OpenDuet
- Instinct vs OpenInstinct
- Instinct vs Orbits
- Instinct vs Orchid
- Instinct vs szn
- Instinct vs Tab
- Instinct vs Zapia
- OpenDuet vs OpenInstinct
- OpenDuet vs Orbits
- OpenDuet vs Orchid
- OpenDuet vs szn
- OpenDuet vs Tab
- OpenDuet vs Zapia
- AstrBot vs Instinct
- AstrBot vs OpenDuet
- Boski vs Instinct
- Boski vs OpenDuet
- Caddy vs Instinct
- Caddy vs OpenDuet
- Claude Duet vs Instinct
- Claude Duet vs OpenDuet
- CowAgent vs Instinct
- CowAgent vs OpenDuet
- folk vs Instinct
- folk vs OpenDuet
- GAIA vs Instinct
- GAIA vs OpenDuet
- Gemini Spark vs Instinct
- Gemini Spark vs OpenDuet
- Grok Bot vs Instinct
- Grok Bot vs OpenDuet
- Haven vs Instinct
- Haven vs OpenDuet
- Hermes Agent vs Instinct
- Hermes Agent vs OpenDuet
- Instinct vs IronClaw
- Instinct vs Leon
- Instinct vs Lindy
- Instinct vs Lobby
- Instinct vs nanobot
- Instinct vs NanoClaw
- Instinct vs Dots
- Instinct vs OpenClaw
- Instinct vs PicoClaw
- Instinct vs Poke
- Instinct vs QwenPaw
- Instinct vs Tasker AI
- Instinct vs Town
- Instinct vs ZeroClaw
- Instinct vs Zo Computer
- 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 Instinct
- Atticus vs OpenDuet
- DeepTutor vs Instinct
- DeepTutor vs OpenDuet
- Hark Pro vs Instinct
- Hark Pro vs OpenDuet
- Instinct vs LearnHarness
- Instinct vs Talorys
- LearnHarness vs OpenDuet
- OpenDuet vs Talorys
- Instinct vs Natura tinyNature
- Instinct vs Pally
- Instinct vs Tomo
- Instinct vs Wajo (Fo)
- Lobby vs OpenDuet
- Natura tinyNature vs OpenDuet
- OpenDuet vs Pally
- OpenDuet vs Tomo
- OpenDuet vs Wajo (Fo)
Disclosure
Instinct 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/instinct-vs-openduet.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/instinct.json·/api/v1/tools/openduet.json - From a terminal
anchor compare instinct openduet(the CLI) - Over MCP
compare_tools {"a": "instinct", "b": "openduet"}at/mcp, no key