Large Language Models

can interpret and execute functions/plugins

a model designed for both function calling and on-device inference

a multi-modal model from Apple

pretraining of a 1.1B Llama model on 3 trillion tokens.

yet another LLM agent framework

a tool for creating and managing memory in LLMs

an attempt to provide ChatGPT with a degree of autonomy

yet another long-running agent tool for complex coding tasks

a multiagent persona simulation

a tool that enables pair programming with LLMs to edit code in local git repositories.

a self-hosted AI coding assistant

Proxy that allows you to use ollama as a copilot like Github copilot

a fork of Claude-Coder for other LLMs

a prototype development tool that leverages GPT

a VSCode extension that uses llm-ls

an Emacs extension for using a local LLM

An open-source alternative to GitHub copilot that runs locally.

a MITM proxy that lets you use the GitHub Copilot extension with other LLMs

An Electron app for macOS

an intriguing personal assistant based on local data

a terminal assistant that leverages tmux

an open-source LLM app development platform with a node-based UX

a node-based GUI for quick iteration of langchain flows

a JavaScript environment for prompt development and structured data extraction for LLMs.

Natural Language Programming against multiple LLMs

a local language server that leverages LLMs

a lightweight NLP toolkit for tasks like fuzzy-deduplication, similarity, and ranking

a tool for compressing prompts with minimal loss of information

a tool for creating and managing LLM workflows

an open-source platform for evaluating, testing, and monitoring LLM applications.

a unified interface for data and feedback collection, including model comparisons

self-hostable toools for evaluating LLMs, vector databases, and prompts

a visual programming environment for benchmarking prompts across multiple LLMs

A tool for testing and evaluating LLM prompt quality.

A local, drop-in replacement for the OpenAI API

an OpenAI gateway in Go to create API keys with rate limits, cost limits and TTLs

An automated installer for LLaMA

an intriguing P2P clustering solution for running models across several machines

a self-hosted inference engine for edge computing with an OpenAI API

A local (edge) inference engine in C++ without any dependencies

a tool that enables inference on AMD GPUs

a PyTorch extension for Intel hardware

A C++ implementation of a GPT-2 inference engine

A C++ port of Facebook’s LLaMA model. Still requires roughly 240GB of (unoptimized) weights, but can run on a 64GB Mac.

A GPU-focused Python wrapper for LLaMa

A Rust port of llama.cpp

another C++ local inference tool

an alternative to Ollama for locally running models

a framework that allows users to serve thousands of fine-tuned models on a single GPU

a set of acceleration techniques

a plugin for Apple Notes that uses the Accessibility APIs

a rudimentary IRC bot that communicates with a local instance of ollama

a bot for integrating ChatGPT and DALL-E into Slack

Recipes for on-device voice AI and local LLM

a CLI wrapper for ChatGPT

CLI to interact with LLMs using markdown and images

a terminal-based interface for LLMs

an easy-to-use AI text-generation software for GGML and GGUF models based on llama.cpp

a web-based interface for LLMs

a more or less sensibly designed self-hosted ChatGPT UI

A containerized solution for using local LLMs via web chat

a set of parsers for common file formats

a search SDK that unifies the entire RAG pipeline in a single database query

a tool for importing and chunking text files for RAG

a data pipeline designed to pre-process knowledge graphs and perform RAG on them

a note taking tool that performs RAG using a local LLM

another framework to create bots from existing datasets

A way to quickly create custom embeddings off a web site

a framework for or rapid development and deployment of production-ready RAG systems with SQLite support

a framework for developing LLM-based applications including Retrieval Augmented Generation

a tool that researches a topic and generates a full-length report with citations

a Perplexity AI search engine clone

a local tool for searching using LLMs

A device that tells bedtime stories to kids, using chunked TTS

automatic generation of visualizations and infographics

A GPTScript tool to generate images

a set of tools for manipulating GGUF format files

a Python script for plotting the intermediate layer outputs of Mistral 7B

LLM training in simple, raw C/CUDA

an implementation of Half-Quadratic Quantization (HQQ)

a way to quantize the LLaMA weights to 4-bit precision

A way to do LoRA adaptation of LLaMa

Another way to do LoRA adaptation of LLaMa

an implementation of word2vec skip-gram for word embedding.

A cross-platform dekstop application with chat history and extension support

an interesting take on how to use semantic search and OpenSearch’s BM25 implementation

an ensemble setup with WhisperSpeech, WhisperLive and Phi

a simple interface for incorporating Agent LLMs

a lightweight library for building Multimodal Agents

a simple, lightweight LLM wrapper

Yet another alternative to langchain

yet another LLM framework using decorators for data validation

a langchain alternative with slighly better internal coding standards

Control modern language models more effectively and efficiently than traditional prompting or chaining.

a composable approach for building LLM applications

a data framework for LLM applications

has spinoffs for chat, workflows for medical/scientific papers, semantic search for developers and semantic search for headlines and story text

Yet another alternative to langchain, but with an interesting approach at defining workflows

a componentized approach to building LLM pipelines

an open-source ChatGPT alternative that runs 100% offline (uses nitro)

a self-hosted local inference front-end for chatting with document collections

another self-hosted local inference front-end

A VS Code notebook interface for LLMs

a Jupyter plugin that can handle code generation and image generation, but not switching models (GPT-4)

a Jupyter plugin that can handle code generation and fixes based on tracebacks

a Jupyter plugin that can handle multiple models

a Python package for serving large language models on Apple silicon.

a lightweight library for efficient text chunking in RAG applications.

a Python library that uses LLMs to perform data cleaning

library for prompting, synthetic data generation, and training workflows

a vactorization library that can handle more than just text

decorators to create functions that return structured output from an LLM.

a package for validating and correcting the outputs of large language models

a memory management/summarization technique for unbounded context

a clever library that simplifies invoking OpenAI function calls

A simple wrapper for the ChatGPT AI

an example of how to do hyrid (vector and FTS) search with SQLite for RAG

tips on how to use OpenAI JSON and function calling

Manual instructions for Apple Silicon

a set of lecture notes and detailed examples of prompting techniques

a collection of LLM resources that operate independently

A set of sample base prompts for various LLMs

Another set of prompting techniques and detailed examples

might be a short-lived resource, but an interesting one

A minimal PyTorch implementation for training your own small LLM

a simple PyTorch-based implementation

a program synthesis agent that autonomously fixes its output by running tests

a simple agent that does online research on any given topic

A pretty hilarious image-to-description example

A self-hosted ChatGPT alternative

provides an example of how to use Graph navigation and Cognitive Search indexing

open-source LLM chatbots

An LLM-powered advanced RAG pipeline built from scratch

A simple interactive web shell with some nice features

a tutorial on how to build a GPT model from scratch

a collection of one-liners for various LLMs

porting of LLMs to tensor processors, starting with the Apple Neural Engine (ANE)

a tool for creating and managing memory-backed agents

an embedding database

A simple vector database that can run in-process

A vector database that performs vector generation internally

A Single-File Vector Search Engine

a pretty complete GPT/search integration solution with GitHub, Slack and Confluence/JIRA connectors

A tutorial on LLM serving using MLX