Models & Infrastructure tools
AI infrastructure covers from model API gateways to local inference. OpenRouter manages hundreds of models with one key, while Ollama runs Llama locally with a single command—keeping data on your machine. Choose based on latency, privacy, and cost priorities.
OpenRouter
AI Tools
One API key, hundreds of models — compare, fall back and rate-limit without the plumbing.
Ollama
AI Tools
The lowest bar for local open models — one command for Llama, Qwen or DeepSeek; data stays on your machine.
Hugging Face
AI Tools
The GitHub of models and datasets — find models, check leaderboards, run demos.
Firecrawl
AI Tools
Clean web-to-markdown/structured-data for LLMs — essential plumbing for content pipelines and RAG.
Replicate
AI Tools
Open models as one-line APIs — image, video and voice, billed by the second.
Together AI
AI Tools
Open-model inference and fine-tuning with strong price-performance and throughput.
Found a great tool?
Submit it — after human review it joins the AI Directory.
Submit a tool