🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Build effective agents using Model Context Protocol and simple workflow patterns

Enhanced ChatGPT Clone: Features Agents, DeepSeek, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message se…

Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching

wasm. bots. 🤖🧙‍♂️🧚🧙‍♀️⚔️🏰🤖

Everything about the SmolLM2 and SmolVLM family of models

An AI memory layer with short- and long-term storage, semantic clustering, and optional memory decay for context-aware applications.

The AI-native proxy server for agents. Arch handles the pesky heavy lifting in building agentic apps - routing prompts to agents or specifc tools, clarifying user inputs, unifying access and observ…

V.I.S.O.R., my in-development AI-powered voice assistant with integrated memory!

Building AI agents, atomically

Declarative framework to build LLM-based applications

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python bindings for llama.cpp

Nexa SDK is a comprehensive toolkit for supporting GGML and ONNX models. It supports text generation, image generation, vision-language models (VLM), Audio Language Model, auto-speech-recognition (…

Generate large synthetic data using an LLM

A very quick project that transforms research papers into engaging three-person discussions, offering an intuitive and thought-provoking listening experience. Perfect for podcast enthusiasts seekin…

LLM inference in C/C++

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Safely execute untrusted Javascript in your Javascript, and execute synchronous code that uses async functions

A high-throughput and memory-efficient inference and serving engine for LLMs

Dockerfile for Apache Kafka

Checksum validator for New Zealand's IRD/GST number.

GraalVM compiles Java applications into native executables that start instantly, scale fast, and use fewer compute resources 🚀

A curated list of awesome resources for Graal, GraalVM, Truffle and related topics

A minimal, resource efficient unikernel for cloud services

A simple C++ interpreter written in JavaScript

A retro game engine for Python

Chromecast local files from Linux - supports MKV, subtitles, 5.1 sound and 4K!

Asynchronous streaming communication for Clojure - web server, web client, and raw TCP/UDP