A Python library for securely persisting and sharing scikit-learn models without using pickle, including tools for creating model cards.

whoami.wiki is a tool that converts personal digital archives like photos and chat logs into a private, encyclopedic wiki about your life.

A token-efficient Slack automation CLI for AI agents that provides zero-config authentication and human-in-the-loop safety controls.

DocuBrowse is an offline, AI‑enhanced document search tool. It indexes a wide range of file types, offers keyword, semantic, and hybrid search (using local Ollama embeddings), provides in‑document “Deep Links”, and can generate AI‑summaries of files with a local model. Everything runs locally, preserving privacy, and the app is packaged for Linux, Windows, and macOS.

A PyTorch library that implements per-step fault tolerance for large-scale training, allowing jobs to continue running even when individual workers or nodes fail.

CC‑Panes is an open‑source desktop app (Windows/macOS/Linux) that lets you run, organise and coordinate multiple AI‑coding CLI agents in parallel. It provides workspace‑level dashboards, reusable launch profiles, an MCP‑based orchestration layer, integrated terminal splits, Git/history tools, planning surfaces, and web/Android access—all built with Tauri, xterm.js and Rust.

Supervisely is a web‑based computer‑vision platform that combines data labeling, model training, inference and collaboration tools. It offers a Python SDK and REST API for automation, and an app ecosystem where developers can create head‑less scripts, interactive UI tools, or labeling‑tool extensions—all deployable with a single click.

A GitHub Action that enables running AI inference via the GitHub Copilot CLI within automated workflows.

A collection of reference implementations of DeepMind's DQN-based reinforcement learning agents, designed for research reproducibility on Atari games.

A tool for simplifying and slimming ONNX models to reduce operator count and improve inference speed while maintaining accuracy.

A memory manager for LLM KV-caches that uses CUDA virtual memory APIs to enable dynamic allocation while maintaining virtual contiguity for unmodified attention kernels.

An AI-powered SQL client and database administration tool supporting multiple popular databases for table design, querying, and synchronization.

An open-source Agentic RAG framework that combines multimodal understanding, ReAct-based agents, and enterprise-grade knowledge management for complex intelligent Q&A.

A PyTorch-based training framework for Stockfish's NNUE evaluation networks, enabling GPU-accelerated training and automated performance evaluation.

A scalable Reinforcement Learning framework specialized for Physical AI applications, providing a decoupled architecture for large-scale training workloads.

A stateless API wrapper for ComfyUI that enables deploying complex generative AI workflows as scalable, production-ready microservices.

An open ABI and FFI for machine learning systems that enables kernel libraries and DSLs to work across multiple frameworks and languages with zero-copy interop.

A comprehensive Ruby API library for OpenAI, providing typed access to the REST API, Realtime WebSockets, and support for Azure and Bedrock providers.

A Python SDK for the Langfuse platform that provides observability, tracing, prompt management, and evaluation tools for LLM applications.

A Python-based framework that allows developers to author, debug, and optimize ONNX models using a natural Python syntax instead of manual graph construction.

A plugin for the LLM CLI tool that provides API access to Google's Gemini models, supporting multimodal inputs and server-side tools like Google Search.

An enterprise-ready proactive AI assistant with a persistent semantic memory layer that integrates with team messaging platforms and prioritizes local-first security.

A JavaScript/TypeScript SDK for the Qdrant vector search engine, providing REST and gRPC clients to manage and search vector data.

An MCP server that gives Claude private, local-first journaling and semantic search capabilities to maintain persistent memory across conversations.

Soar is a cognitive architecture for developing systems that exhibit intelligent behavior, providing a framework for reasoning and problem-solving.

Custom ComfyUI nodes that integrate Depth Anything V3 for high-quality depth estimation, 3D point cloud reconstruction, and consistent video depth mapping.

An automated document processor that uses local Vision AI via Ollama to analyze scanned PDFs and automatically rename them with descriptive filenames.

A machine learning framework built on TorchRL for algorithmic trading that supports RL, LLMs, and rule-based strategies for both backtesting and live deployment.

An AI-native Python client for Redis that provides tools for vector search, hybrid search, and production-ready extensions for LLM memory and semantic caching.

An AI-native SDLC workflow for Java Enterprise applications that provides reusable skills, agents, and commands to standardize analysis, design, and implementation.

NVIDIA's centralized hub for JAX and XLA on GPUs, providing optimized container images, technical documentation, and performance tuning for AI workloads.

RFUAV provides a publicly‑available RF‑signal dataset for UAV detection/identification, along with Python/MATLAB tools to turn raw IQ recordings into spectrograms, train vision‑style classifiers (ResNet, ViT, etc.) or YOLOv5 detectors, and evaluate performance across a wide SNR range.

A CLI tool that allows users to instantly switch between different Anthropic-compatible AI providers and local backends when using the Claude Code CLI.

An MCP server that enables any AI assistant to discover and use Claude Agent Skills through semantic search and a performance-optimized two-package architecture.

A collection of over 100 web interaction environments for training and AI agents to interact with web browsers using the Gymnasium API and Selenium.

A Korean morphological analyzer for Python that provides tokenization, part-of-speech tagging, and advanced typo and dialect correction.

A high-performance Python SDK and runtime for building LLM agents, featuring both autonomous ReAct agents and structured workflow orchestration with state recovery.

An AI-powered data analysis tool that allows users to upload CSV files and generate interactive charts using Llama 3.1 and the E2B Sandbox.

A Python toolbox for facial expression research that detects faces and extracts emotional expressions, facial muscle movements, and landmarks from images and videos.

An experimental communications API for PyTorch that provides a high-level collectives interface and support for multiple hardware backends like NCCL, RCCL, and XCCL.

A distributed infrastructure framework that enables individuals to manage PB-level data warehouses, large-scale scraping, and task orchestration with the capacity of a large organization.

DP‑GEN is a Python platform that automates the creation of deep‑learning interatomic potentials (Deep Potential models). It runs a concurrent learning loop—sampling structures, selecting the most informative ones for DFT calculations, and retraining the model—while handling job scheduling on HPC clusters and interfacing with many MD and quantum‑chemistry codes.

A plugin for the LLM CLI utility that enables access to a wide variety of AI models hosted by OpenRouter, including support for vision, structured outputs, and hosted server tools.

An open-source universal voice-to-text interface that uses AI to transcribe and format speech into clean text, typing it directly into any active application.

A multi-modal data loader for Megatron-LM that enables scalable, distributed loading and blending of massive datasets for training large models.

A text-based virtual environment for benchmarking AI agents on tasks derived from a standardized elementary science curriculum.

A Model Context Protocol (MCP) server that enables LLMs to perform reasoning-based, vectorless RAG over long PDFs using hierarchical tree structures.

A general framework for benchmarking different vector search engines under the same hardware constraints to compare their performance and efficiency.