Minimal llama.cpp embedding wrapper for Harper Fabric. Talks directly to the native addon — no build tools, no CLI, no chat wrappers.
lezer-based C++ grammar
Pi extension for llama.cpp integration. Supports both router and single modes.
Unified high-level interface for local LLMs – supports Ollama (remote/local server) and embedded node-llama-cpp (GGUF models) with chat sessions and tool calling
This module provides native bindings to ecdsa secp256k1 functions
C++ grammar for tree-sitter
KINDX - On-device hybrid search engine for markdown documents with BM25, vector embeddings, and LLM reranking
JS tokenizer for LLaMA-based LLMs
Native Abstractions for Node.js: C++ header for Node 0.8 -> 26 compatibility
Four-layer local memory system plugin for OpenClaw — auto-captures, structures, and profiles conversational knowledge using local LLM + SQLite vector search (L0→L1→L2→L3 pipeline)
The official TypeScript library for the Llama Stack Client API
Slice GeoJSON data into vector tiles efficiently
Node.js package to access serial ports. Linux, OSX and Windows. Welcome your robotic JavaScript overlords. Better yet, program them!
Install all the tools required for building and testing C++/C projects.
## Installation
Chat UI and Local API for the Llama models
event-based workflow engine
Run LLMs locally in your terminal. Supports custom .pt GPT-2 and LLaMA decoder checkpoints (auto-handles compact key naming, tied embeddings, and split-halves RoPE) plus GGUF models, with a live dashboard of throughput, VRAM, and chat.
> [!WARNING] > This package has been deprecated since version 4.1.0. > Please migrate to [llama-cloud-services](https://www.npmjs.com/package/llama-cloud-services). > See the documentation: https://docs.cloud.llamaindex.ai
The official TypeScript library for the Llama Cloud API
Helpers for installing and using Whisper.cpp
Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
A minimal llama.cpp provider for the Vercel AI SDK implementing LanguageModelV4 and EmbeddingModelV4
realistic password strength estimation