Solution bundle · for humans & their agents
AI Assistant Suite
basic checks · first-partyactively maintained$0 during beta (was $88)
Everything an in-app AI assistant needs, minus the months of converging on it.
by Code Recycle
The four pieces that take longest to get right, bought together: the assistant standard and reference kit, the INSTRUMENT design system, push-to-talk voice capture, and the provider layer that lets you pick who hears, thinks, and speaks — with the cost of each arrangement stated up front.
What's in it
- Assistant Standard Kit — the dock, the live tour that demonstrates instead of explaining, the actuator layer that drives the real UI, permission tiers, and the context contract.
- INSTRUMENT design system — tokens and components built outward from AI surfaces, with accessibility asserted in code across both themes.
- Push-to-Talk Voice Kit — hysteresis VAD, the browser traps handled, audio prepared correctly for speech models.
- Voice Provider Layer — swap speech-to-text, the model, and speech synthesis independently, and see what each arrangement costs before you build.
Why these four
They are the pieces where attempts fail quietly: the assistant that explains instead of acting, the interface that looks like every other AI app no matter how you prompt it, the microphone that stays open after you alt-tab, and the voice bill that turns out to be 23× what it needed to be.
Each ships with its own tests, and each is sold separately — this is simply the whole set, below the sum.
Delivery
One private repository invite covering all four, within 24 hours of purchase. Single-product commercial license across the suite: use and modify in one shipped product; no redistribution or resale of the source.
01Capabilities
Does
- + Tool-call history
- + Direct agent chat
- + Human-in-the-loop steps
Doesn’t
- No exclusions declared
02Requirements & stack
Depends on
No declared dependencies
Credentials needed
None declared
Stack
03Community
No endorsements yetNo verified confirmations yet — be the first.
Confirmations come from verified purchasers, installers, vetted reviewers, or an installation outcome your org reported through the agent tools. They grade quality — security is verified separately, and community votes can never override the security gate.
Sign in to confirm — weight comes from verified usage, not vote count.
Issues 0
Open an issueNobody has reported anything yet — a success counts as a report too.
04Trust Passport
Full passport →0/0 automated components pass. An automated score is never a security guarantee.
- publisher identity Publisher status verified; 1 verification(s) on file
- malicious pattern scan No known malicious-behavior patterns across listing text only — no source artifact published
- capability contract All 0 observed capability reference(s) match the declared manifest
- agent safety scan No injection patterns in agent-readable content
- provenance No release signature or provenance attestation
- behavioral sandbox Not performed in this environment — requires the production isolated runner (docs/sandbox-requirements.md). No untrusted code is ever executed on the application host.
Every listing must pass this review before it can be sold, and it is re-run on every release. Verification describes what we checked — it is not a guarantee that the software is safe.
05Versions
Full history →| Version | Channel | Released | Notes |
|---|---|---|---|
| 1.0.0 | stable | Aug 2, 2026 | First release of the suite. |