JS tokenizer for LLaMA 3

The **[DeepInfra provider](https://ai-sdk.dev/providers/ai-sdk-providers/deepinfra)** for the [AI SDK](https://ai-sdk.dev/docs) contains language model support for the DeepInfra API, giving you access to models like Llama 3, Mixtral, and other state-of-th

Terminal AI Chatbot using LLaMA 3

Unbranded conversational search widget - keyword-only or optional AI (Llama 3)

Terminal AI Chatbot using LLaMA 3

On-device LLM inference for React Native — Gemma 4, Gemma 3, Phi-4, Mistral, Llama 3 and more via Google AI Edge LiteRT-LM, ML Kit AICore and MediaPipe

Autonomous HTTP 402 Web Scraper, Edge Llama-3 Digest, Security Audit & Twitter Intelligence Action Provider for Coinbase AgentKit on Base L2

Meta Llama 3 vocabulary for hypertok format version 1

Bring Replicate-hosted models to Hivekeep — LLM (Llama 3, Mistral, Mixtral), Image (Flux Schnell, Stable Diffusion 3.5), and Embedding — all behind one API token.

Terminal AI Chatbot using LLaMA 3

The zero-latency fault tolerant WebGPU runtime for React. Run Llama-3, Phi-3, and Gemma directly in the browser with privacy-first local inference.

Prebuilt binary for node-llama-cpp for Linux x64

Terminal AI Chatbot using LLaMA 3

Extension of @node-llama-cpp/linux-x64-cuda - prebuilt binary for node-llama-cpp for Linux x64 with CUDA support

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Prebuilt binary for node-llama-cpp for Linux x64 with Vulkan support

Prebuilt binary for node-llama-cpp for Linux arm64

Prebuilt binary for node-llama-cpp for Linux armv7l

Prebuilt binary for node-llama-cpp for Linux x64 with CUDA support

Terminal AI Chatbot using LLaMA 3