Official Node + browser SDK for Ollama. ESM-first, typed, streaming.
Editorial verdict: “Foundational primitive for Node + browser apps against Ollama. ESM-native, typed.”
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
For Node and browser developers who want a typed, streaming bridge to Ollama without reinventing HTTP calls. This is the official SDK, so it tracks Ollama’s API surface closely and ships ESM-native with full TypeScript definitions. Streaming works in the browser once you configure CORS on the Ollama server — a one-time setup that’s worth the trade-off for real-time chat UIs. It’s fully offline by design, since Ollama runs locally, and works across Linux, macOS, Windows, and the web. Just know it’s Ollama-specific: if you later switch runtimes, you’ll swap SDKs entirely.
Thin SDK / proxy / compatibility layer.
Best universal LLM proxy. Foundational layer for multi-provider deployments.
Foundational primitive for Python scripts against Ollama. Official, maintained, typed.
Cloud-only LLM router. Useful category, novel pricing. The 'unlimited' math has a known failure mode at heavy usage.
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.