Deploy any AI model, agent, database, RAG, and pipeline locally or remotely in minutes

Standalone C++ implementation of Moonshine ASR with ONNXRuntime

The official website of SUPERB Benchmark

Simple examples using Argilla tools to build AI

A wrapper around speech quality metrics MOSNet, BSSEval, STOI, PESQ, SRMR, SISDR

Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

A curated list of AI-powered coding tools

Code of NIPS18 Paper: BRITS: Bidirectional Recurrent Imputation for Time Series

Ultra-lightweight AI Agent

The best way to create and build MCP Servers

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

Omnara (YC S25) - Talk to Your AI Agents from Anywhere!

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.

Renderer for the harmony response format to be used with gpt-oss

The glamourous AI coding agent for your favourite terminal 💘

Your unified, shareable memory layer for AI apps. Compatible with Cursor, Claude Desktop, Claude Code, Gemini CLI, Windsurf, AWS's Kiro, VSCode, Cline

Architecture decision record (ADR) examples for software planning, IT leadership, and template documentation

Rules and Knowledge to work better with agents such as Claude Code or Cursor

LLM tools for running queries against SQLite

PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.

Claude Code dashboard with usage stats, error analysis, and sharable feature

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M-series) chips. It implements OpenAI-compatible API endpoints, enabling seaml…

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

This repository will be a community-curated list of software and resources that explicitly avoid the integration of artificial intelligence.

The AI coding agent built for the terminal.