Modal
Cloud serverless compute with second-scale GPU scaling — ideal for AI backends.
Why it's listed
If your AI workloads come in bursts, Modal scales GPU resources up and down in seconds so you only pay for what you use. It’s ideal for training and inference backends where idle instances waste money.
In the same category
OpenRouter
One API key, hundreds of models — compare, fall back and rate-limit without the plumbing.
Ollama
The lowest bar for local open models — one command for Llama, Qwen or DeepSeek; data stays on your machine.
Hugging Face
The GitHub of models and datasets — find models, check leaderboards, run demos.
Firecrawl
Clean web-to-markdown/structured-data for LLMs — essential plumbing for content pipelines and RAG.
Related skills (Agent Skills)
Anthropic Agent Skills
Anthropic's official skills repo — the de facto reference set for the SKILL.md format.
Visit websiteSuperpowers
The most influential agent-skills collection: TDD, plan-first and debugging methodology, installable.
Visit websiteRelated
Linked by topic, people and hubs
Found a great tool?
Submit it — after human review it joins the AI Directory.
Submit a tool