Parse files (e.g. code repos) to clipboard or a file for ingestions by AI / LLMs

Review/Check GGUF files and estimate the memory usage and maximum tokens per second.

An OpenAI API compatible API for chat with image input and questions about the images. aka Multimodal.

WebAssembly binding for llama.cpp - Enabling in-browser LLM inference

YAML parser and stringifier for JavaScript

A tool that helps you build prompts with lots of code blocks in them.

JS tokenizer for LLaMA 3 and LLaMA 3.1

Run LLMs locally with as little friction as possible.

Improved file parsing for LLM’s

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

CLI tool for converting GeoJSON files to SQLite (with SpatiaLite)

TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

JS tokenizer for LLaMA 1 and 2

Promptman is a small helper for repetitive prompt engineering techniques

Empower your LLM to do more than you ever thought possible with these state-of-the-art prompt templates.

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

LlamaIndex is a data framework for your LLM applications

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

🦜🔗 Build context-aware reasoning applications

Python bindings for llama.cpp

LLM inference in C/C

Official supported Python bindings for llama.cpp gpt4all

gpt4all and llama typescript bindings

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.