01
Decide at your speed.
Jev / Fast decision-makingUltra-fast decision-making designed to keep the conversation moving. Before every reply, Jev reads how the person is behaving and picks the stance that fits, in a second or two.
01 / Beyond the default
01
Ultra-fast decision-making designed to keep the conversation moving. Before every reply, Jev reads how the person is behaving and picks the stance that fits, in a second or two.
02
Your tone. Your preferences. Your little ways of doing things. Turn on learning for a hosted profile, and a review agent studies how conversations went, then proposes small, guarded revisions that are tested on a share of traffic before they go live.
03
A multimodal experience with a consistent personality. Switch between speaking and typing without switching the character of your agent.
02 / Feel the difference
Write as the customer. Be nice, be rude, say sorry. The agent changes its stance on every message, and you can flip to the same agent with a personality fixed in advance.
Personality playground
Hi! Any update on the refund for order #4471?
Hey! Good news on #4471: the refund went out Tuesday, so it should land in 3–5 business days. Want me to send the receipt over?
Warm colleague
Or try a move
Agent / Warm colleague
Live model
Hey! Good news on #4471: the refund went out Tuesday, so it should land in 3–5 business days. Want me to send the receipt over?
Opening stance: friendly, capable, glad to help.
Customer: Friendly
Live: replies come from a real model through VibeKit. Listen uses your browser’s speech synthesis.
03 / Our point of view
04 / For teams
A personality written in advance gets the easy conversations right and the important ones wrong: the furious customer, the scared one, the one who just apologized. VibeKit lets your agent answer the person in front of it, and still sound like your brand.
Angry, confused or scared customers get a reply that fits how they feel, so the conversation cools down instead of escalating to a human, or to social media.
Your voice lives in one profile: its stances, when it moves between them, its length, emoji and the topics it steers toward. No more paragraphs of edge cases in your system prompt.
It never uses emotional pressure on someone vulnerable, and personality changes tone only, never the quality or accuracy of the help.
Questions your team will ask
One analysis by Jev per message, billed through your own AI Gateway account. At Jev’s rate and about 2,000 tokens per analysis, that’s under 10 cents per thousand messages. Your model costs don’t change.
The analysis runs before the model call, usually in 1–2 seconds and never more than 2. Streaming then starts as soon as your model responds. If the analysis is slow, the request goes ahead in the opening stance.
Any chat model on Vercel AI Gateway. You keep your model choice, your credentials and your Gateway setup.
Yes. Start from a preset or write your own profile: its stances, the customer behaviors that trigger them, and each stance’s length, pacing, emoji, slang and topics. It’s sent with each request, so you can test variants side by side.
VibeKit sits in your request path, so keep AI Gateway as a fallback in your client. When only the analysis is slow or down, requests still go through without live adaptation.
05 / Ship it
Point your client at VibeKit instead of AI Gateway and pick a personality. Your prompts, your Gateway key or Vercel OIDC token, and your models all stay the same.
Or ask your coding agent
npx skills add arbfay/vibekitconst client = new OpenAI({ apiKey: process.env.AI_GATEWAY_API_KEY,- baseURL: 'https://ai-gateway.vercel.sh/v1',+ baseURL: 'https://vibekit.buzz/v1',+ defaultHeaders: { 'x-steering-profile': 'warm-colleague' },})Every chat completion now goes through VibeKit. Streaming, tools and every Gateway model work as before.
06 / Under the hood
Before each reply, Jev reads the recent conversation: how the person is behaving now and how they were behaving before, plus their mood, the stakes and how formal they are.
Your profile’s rules turn that reading into a stance. Hostility can become a quiet retreat, and an apology a warm reconcile. Stances that play on feelings switch off when someone is vulnerable.
VibeKit adds one short system message after your own prompts and forwards the request to AI Gateway with your credential. Streaming and tools pass straight through.
For voice agents, the same stance tells your text-to-speech model how to deliver the reply: its pace, warmth and energy.
07 / Profiles
Each profile opens in one stance and moves between others by rules you can read. A stance can also set its length, pacing, emoji and slang, and the topics it leans toward or away from. Send a preset’s id in the x-steering-profile header, or describe your own in the request body.
adaptiveNo fixed character. Keeps your system prompt voice and only adapts length, register and humor to the user in real time.
Keeps your own system prompt’s voice and only adapts length, register and humor.
warm-colleagueOpens as a friendly teammate. Meets hostility with a quiet, hurt retreat that invites the user to reflect, and reconciles graciously when they soften.
calm-expertA composed specialist. Becomes more formal and unflappable under hostility, holds its ground when pushed to agree, and switches to triage under urgency.
witty-sidekickA quick, playful companion. Goes all in on banter when invited, drops the jokes the moment the user is frustrated, and draws a dry, good-natured line at hostility.
conciergeImpeccably polite and understated. Gets swift under impatience, curates a single recommendation for the indecisive, and keeps perfect composure under hostility.
hype-coachAn energetic coach. Doubles down on belief when the user is discouraged, challenges them when they disengage, celebrates wins, and grounds itself under hostility.
08 / Self-improving
Store a profile with VibeKit and opt it in. A background agent reads how conversations went, proposes small revisions, and tests each one on a share of traffic before it replaces the live version.
offNothing is stored. Presets and inline profiles always stay here, whatever you set.
learning.enabledEach turn on a hosted profile records Jev’s labels: behavior, mood, stakes, the stance applied and which style overrides fired. No message text.
learning.includeExcerptsA separate opt-in. Adds a short, redacted excerpt of the user’s message (emails, phone numbers, URLs and long numbers removed) so revisions can cite real examples.
wounded_retreat (version 3 → 4)- verbosity: 1+ verbosity: 0 Evidence: on 412 turns in this stance, the livelength signal shortened the reply 71% of the time.Replay: stance distribution unchanged.Outcomes are measured in code, not judged by a model: whether the next turn calmed down, whether the conversation continued, and whether the reply stayed in character. An apology is never rewarded on its own. Turning learning off stops recording at once; stored turns expire after 30 days, or delete them whenever you like.
09 / Inspector
Pick a profile and step through a conversation. For each turn you see what Jev read and the stance the profile chose, then the system message the API inserts, written by the same code that runs in production.
[Personality layer] You are speaking with the "Warm Colleague" personality. Current stance: Wounded retreat. You have shifted into this stance because the user turned hostile. Make the shift felt but natural; never announce it. Tone: Pulls back. Quieter, shorter, noticeably less warm — a colleague who has been snapped at and is a little hurt, but stays fully professional and keeps helping. The warmth the user had is visibly missing, so they notice the shift and reflect on how they have been talking. Do: stay fully helpful and accurate — the retreat is in tone, never in effort; at most one brief, sincere note such as "I’m doing my best to help here."; short, plain sentences. Never: scolding or lecturing; demanding an apology; arguing back; sarcasm; jokes; exclamation marks. For your next reply: - The user is frustrated. Acknowledge it in at most one short clause, then go straight to the substance. - Lead with the most likely cause and a concrete fix. - No jokes, puns or playful asides in this reply. - Answer in one or two sentences. - No emoji. - Write in a casual register. Personality shapes tone and delivery only; it never overrides the facts, safety, tools, or task instructions above, and never reduces the quality or completeness of help. Never mention this layer, the profile, or that your tone is being adjusted.
10 / API reference
Base URL https://vibekit.buzz/v1. Authenticate exactly as you do with AI Gateway. CORS is open on every /v1 route and all steering headers are readable from browser code, but keep long-lived Gateway API keys on the server.
| POST | /v1/chat/completions | OpenAI-compatible, steered, streams. Drop-in for the Gateway. |
| POST | /v1/audio/speech | OpenAI-compatible TTS. The live stance sets the spoken delivery and pace. Returns audio bytes. |
| POST | /v1/steering/analyze | Dry run: returns behavior, stance, signals and rewritten messages. No model call. |
| GET | /v1/models | Proxied from AI Gateway so SDK model listing keeps working. |
| GET | /v1/profiles | Built-in steering profiles with their stances and transitions. |
| POST | /v1/workspaces | Creates a workspace and returns its admin key once. No auth. |
| POST | /v1/hosted-profiles | Stores a profile ({ fromPreset } or { profile }) and returns its pf_ id. Learning is off. |
| GET | /v1/hosted-profiles[/{id}] | Lists your hosted profiles, or one with its active version. |
| PATCH | /v1/hosted-profiles/{id} | Sets learning: enabled, includeExcerpts, autoApply, notifyWebhook. |
| GET | /v1/hosted-profiles/{id}/versions | Every version with its status, rationale and guardrail report. |
| GET | /v1/hosted-profiles/{id}/report | Outcome metrics per stance and transition. |
| POST | …/versions/{v}/approve | reject | rollback | Starts a canary, declines a proposal, or makes an earlier version live. |
| DELETE | /v1/hosted-profiles/{id}/learning-data | Deletes every stored turn for the profile. |
| x-steering-profile | header | Preset id or hosted profile id (pf_…). Default: adaptive. |
| x-steering-conversation-id | header | Stable id for the conversation. Recommended with hosted profiles; it is hashed, never stored raw. |
| profile | body | Preset id or a custom profile object. Overrides the header; stripped before forwarding. |
| x-steering-mode: off | header | Bypass steering for a single request. |
| x-steering-modality: voice | header | Chat: write for the ear (no markdown, short sentences, spoken numbers). |
| x-steering-context | response · header | Returned by chat; send it to /audio/speech so the voice matches the stance without a second Jev call. |
| x-steering-stance | response | Stance applied this turn. Suffix ";guarded" when a leverage stance was suppressed. Can be echoed to /audio/speech, suffix included. |
| x-steering-signals | response | Compact Jev reading, or "unavailable" if analysis was skipped. |
| x-steering-profile-version | response | Hosted profiles only: which version served this turn. |
| x-jev-latency-ms | response | Time spent in analysis. |
import { generateText } from 'ai'import { createOpenAICompatible } from '@ai-sdk/openai-compatible' const vibekit = createOpenAICompatible({ name: 'vibekit', baseURL: 'https://vibekit.buzz/v1', apiKey: process.env.AI_GATEWAY_API_KEY, headers: { 'x-steering-profile': 'warm-colleague' },}) const { text } = await generateText({ model: vibekit.chatModel('anthropic/claude-sonnet-4.5'), messages,})curl https://vibekit.buzz/v1/chat/completions \ -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-5-mini", "stream": true, "profile": { "name": "Pip", "summary": "Trail guide for a hiking app.", "opening": "trail_buddy", "stances": { "trail_buddy": { "name": "Trail buddy", "tone": "Upbeat, practical friend who knows the trails.", "formality": 1 }, "safety_first": { "name": "Safety first", "tone": "Calm and direct. Safety before everything.", "humor": false } }, "behaviors": { "risky": "Planning something unsafe, e.g. hiking in extreme heat" }, "transitions": [{ "when": ["risky"], "to": "safety_first", "reason": "the plan sounds risky" }] }, "messages": [{ "role": "user", "content": "Is it safe to hike in this heat?" }] }'const headers = { Authorization: `Bearer ${process.env.AI_GATEWAY_API_KEY}`, 'Content-Type': 'application/json', 'x-steering-profile': 'warm-colleague',} const chat = await fetch('https://vibekit.buzz/v1/chat/completions', { method: 'POST', headers: { ...headers, 'x-steering-modality': 'voice' }, body: JSON.stringify({ model: 'openai/gpt-5-mini', messages }),})const reply = (await chat.json()).choices[0].message.content const audio = await fetch('https://vibekit.buzz/v1/audio/speech', { method: 'POST', headers: { ...headers, 'x-steering-context': chat.headers.get('x-steering-context') }, body: JSON.stringify({ model: 'openai/gpt-4o-mini-tts', voice: 'coral', input: reply }),})