AI Chat
A complete AI workspace: chat with streaming Markdown, voice in and out, image generation, and a managed document
library that grounds answers in your own files. This is the pack-ai-chat pack. It is the largest pack in the catalog,
and the one the Aether template is built on.
What you need
- An OpenAI API key. It covers text, transcription, speech, realtime voice, and embeddings out of the box.
- Optionally Anthropic or Google keys, to route the text model elsewhere.
- A billing pack. Usage is metered against the organization's plan, so this pack depends on the
pack-billingfamily and refuses to install without one. - Postgres, Valkey, and RustFS (uploads and generated images land in a private bucket).
What it depends on
- A starter pack, for auth, organizations, and permissions.
- A billing pack: Stripe, Lemon Squeezy, or Polar.
What you get
/chat: conversation history, streaming responses, dictation, read-aloud, and image generation, on web and in the Expo app./knowledge: upload documents, watch them index, and have answers cite them. Versioned, with per-organization limits.- Durable execution. Every run and tool call is a row, so a run that dies mid-stream is recovered by a job, and cancellation is a state change, not a dropped socket.
- Usage accounting per organization: tokens, operations, voice minutes, and storage, reserved before a run and settled after, against caps from the plan.
- In the admin app: an AI usage dashboard with 30-day charts, a workspace leaderboard against plan caps, and an AI usage tab on every organization for its allowance and model mix.
Background jobs
Two cron jobs register with the template's scheduler on install:
| Job | Schedule | What it does |
|---|---|---|
ai-chat-recovery | every 30 seconds | Finishes or fails runs whose process died |
knowledge-indexing | every 5 seconds | Chunks and embeds newly uploaded documents |
They start with the API, so nothing extra runs in production. See Scheduled jobs.
Environment variables
| Variable | Purpose |
|---|---|
OPENAI_API_KEY | Required |
ANTHROPIC_API_KEY, GOOGLE_GENERATIVE_AI_API_KEY | Optional, for other text providers |
AI_TEXT_MODEL | provider:model, default openai:gpt-5.4-mini |
AI_TRANSCRIPTION_MODEL, AI_SPEECH_MODEL, AI_REALTIME_MODEL | Voice models |
AI_STORAGE_BUCKET | Private bucket for uploads and images, default ai-private |
AI_MAX_OUTPUT_TOKENS, AI_MAX_RUN_SECONDS, AI_MAX_VOICE_SECONDS | Hard caps per run |
AI_USER_STORAGE_BYTES | Storage cap per user |
KNOWLEDGE_EMBEDDING_MODEL | Embedding model for the document library |
KNOWLEDGE_MAX_FILE_BYTES, KNOWLEDGE_MAX_PAGES, KNOWLEDGE_MAX_TEXT_CHARACTERS | Upload limits |
Every cap has a sensible default. You only need OPENAI_API_KEY to start.
After installing
The pack adds eleven Prisma models (conversations, messages, runs, tool calls, assets, voice sessions, usage accounts
and reservations, knowledge documents, versions, and chunks). Say yes when the CLI offers to run the migration, or run
pnpm --filter @hype-stack/backend migration:create afterwards.
Related
- Aether, the template built on this pack
- Billing (Stripe) for the plan caps usage is metered against
- Storage for the private bucket
Every purchase and sponsorship funds my 8+ years of work on open source given freely to the community. It keeps the lights on, funds new packs, and keeps the ecosystem alive. Even a small tier means a lot. Thank you!