Every idea in this repo leans on one of four AIsa kernels. Each one runs against the public AIsa API with a single key, so you ship a real demo with zero infra and no provider-shopping.
Kernel: an OpenAI-compatible `POST /v1/chat/completions` against https://api.aisa.one/v1 — pick any frontier model (openai/gpt-4o-mini, anthropic/claude-3-5-sonnet, google/gemini-2.5-flash, qwen/qwen2.5-72b, deepseek/deepseek-chat) through one endpoint, one key
UI: a prompt box or chat surface that returns markdown the user can read, copy, or act on
Kernel: an OpenAI-compatible `POST /v1/images/generations` against https://api.aisa.one/v1 (Seedream + GPT image backends) — returns a hosted URL the client renders straight into an <img>
UI: a prompt-driven canvas that renders covers, moodboards, posters or scene art on demand
Kernel: the AIsa Media Gen skill (Wan / Seed video models) submitted via `POST /v1/skills/mediagen` — returns a task id, the client polls until an MP4 URL is ready
UI: a prompt → progress bar → playable MP4 surface for short motion sketches, loops, or scene reels
Kernel: AIsa Agent Skills (`POST /v1/skills/{skill_id}`) — web search (Tavily / Perplexity), YouTube SERP, Twitter, scholar, markets, trends — typed JSON results fed back into the LLM for grounded answers
UI: a search/topic box that returns citation-grade results, trend signals, or research the user can drop into the work
Add this to your Lovable project (Project Settings → Secrets). It stays on the server, read by your TanStack server function via process.env.AISA_API_KEY.
AISA_API_KEYSingle API key that unlocks chat (every frontier LLM), image (Seedream + GPT image), video (Wan + Seed) and Skills (Tavily search, YouTube, scholar, markets). Free tier covers a hackathon weekend.