MCP and API pages
Run AISLE on X
52 tools, one MCP server. The only decision is which model calls it and which GPU backs the calls that need pixels.
The stack, in order
4 seats
Model
also does this job Jasper, Copy.ai, Rytr, ChatGPT · the Copy and LLM shelf →
GPU
also does this job Modal, Lambda, Vast, Together and 7 more · the GPU and cloud shelf →
Local weights
also does this job Sora, Google Veo, Kling, Luma Dream Machine and 11 more · the Video shelf →
API gateway
also does this job Portkey, Revana, Kie.ai, APIMart and 1 more · the API gateway shelf →
A pick is the first paid option in a seat. The free route is the $0 path through the same job. A seat with one pick still lists the other paid tools that do the job.
The $0 route
4 of 4 seats
- Model Claude, GPT, Qwen
- GPU Ollama
- Local weights Wan 2.2, LTX-Video
- API gateway LiteLLM, OpenRouter, Cloudflare AI Gateway
Other moments
same index
Recreate this
A teardown names the shots, the beats and the hook.
Rebuild the post →Source it
A product page answers what to sell.
Find the supplier →Validate it
Before the stock order: is anyone already selling this, and what do they charge.
Check demand →Direct and generate the film
Story to stitch: look, original AI cast, shot board, generation, consistency and the final cut.
Direct the film →Clip and edit this
The video is already proven.
Cut it →Write 50 more
One hook is a post.
Write the set →