A library for fast, large-scale approximate nearest neighbor search using space partition trees and relative neighborhood graphs.

A Python package for writing, manipulating, and running quantum circuits on quantum computers and simulators, optimized for NISQ-era hardware.

An open-source TypeScript SDK for running autonomous AI agents in-process, featuring a vast library of built-in tools and support for multiple LLM providers.

A collection of standardized experiments and benchmarks for evaluating the core capabilities of reinforcement learning agents to facilitate reproducible research.

PyTorch Benchmarks is a collection of standardized, lightweight versions of popular deep‑learning models (BERT, ResNet, Stable Diffusion, etc.) that can be run to measure the performance of different PyTorch builds, CUDA versions, and back‑ends. It offers a uniform API, install scripts, and multiple runners (simple test, pytest‑benchmark, custom userbenchmark) plus utilities for low‑noise tuning on AWS g4dn.metal instances.

A C++ library for performing arbitrary optimizations on ONNX models, providing shared optimization passes to be reused across different backend implementations.

A framework for integrating machine learning into LLVM to replace human-crafted compiler optimization heuristics with trained models.

TorchLens is a Python library for capturing, visualizing, and intervening on the full computational graph of any PyTorch model (and preview support for other frameworks). It records every activation and gradient, provides rich per‑operation metadata, lets you query or filter tensors, draw PDF graphs, compute receptive/projective fields, and replay or modify the graph for “what‑if” experiments. The tool is validated on >11 600 architectures, with ~89 % algorithmically verified for faithful capture.

A fast and extensible library for training, evaluating, interpreting, and serving decision forest models like Random Forest and Gradient Boosted Trees.

An MCP server that gives AI agents unfiltered access to a local shell and file system for autonomous coding, building, and running of software.

A framework and benchmark for developing Multimodal Large Language Models capable of deep research through iterative visual and textual search across images and videos.

A LiDAR-augmented system that combines Gaussian Splatting and neural Signed Distance Fields (SDF) for geometrically consistent photorealistic rendering and 3D surface reconstruction.

A local orchestration tool that uses multiple AI subscriptions to provide parallel, multi-vendor code reviews to catch bugs and biases that a single AI model would miss.

A library of high-performance CUDA kernels for linear attention variants like KDA and Lightning Attention, optimized for NVIDIA Blackwell and Hopper GPUs.

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

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

A multilingual visual dashboard for the Hermes agentic orchestration system that makes multi-agent delegation and kanban task tracking visible and manageable from a browser.

A Model Context Protocol server that gives AI agents access to Mapbox's location intelligence, enabling geospatial reasoning, routing, and interactive map visualization.

An in-container GPU resource controller that intercepts CUDA calls to enforce per-container memory and compute utilization limits without modifying applications or drivers.

An open-source, model-neutral coding agent with a Rust runtime that supports Desktop and TUI interfaces for private and enterprise environments.

lionagi is a Python library and CLI for building, running, and governing multi‑agent LLM workflows. It offers typed, persisted conversation state, supports parallel fan‑outs and DAG‑based flows, integrates both model‑specific CLIs and API providers, and includes a web UI (Lion Studio) for visual run management.

A secure, policy-enforced execution gateway for AI agents that intercepts and governs file, network, process, and database activity at runtime.

An open-source deployment platform featuring an autonomous AI agent that handles app deployment, configuration generation, and self-healing fixes.

A comprehensive software development kit that bundles headers, bindings, and loaders for developing cross-platform OpenCL applications.

A Swift/Metal library for rendering 3D Gaussian Splats on Apple platforms, enabling real-time visualization of 3D scenes on iOS, macOS, and visionOS.

UnisonDB is an open‑source, log‑native real‑time database built for edge AI. It stores data in a B+‑Tree (BoltDB or LMDB) while streaming every write via a write‑ahead log that can be replicated over gRPC or object‑store (S3/MinIO). The system offers Raft‑based high‑availability writes, sub‑millisecond change notifications, and multi‑model support (KV, wide‑column, large objects), enabling thousands of edge nodes to stay in sync without separate streaming infrastructure.

A low-code AI application development platform that enables users to build, orchestrate, and deploy complex AI workflows and agents using a visual interface.

A connector middleware that enables AI agents to join and participate in video calls on platforms like Zoom, Google Meet, and Microsoft Teams via voice and chat.

A TUI application for managing and chatting with local Ollama models and major cloud LLM providers in a single terminal interface.

A Chrome extension AI web agent that runs entirely on-device using WebGPU, allowing users to automate web tasks privately and for free without cloud APIs.

DreamX-World is a general-purpose interactive world model that generates high-fidelity, controllable simulations allowing users to explore and transform environments via event prompts.

An MCP server that connects AI assistants to the Gemini/Antigravity CLI, enabling large-scale codebase analysis and sandboxed code execution.

An AI-powered research tool that automates the gathering of information from the web and local files to generate comprehensive, in-depth reports.

Bindu is an open‑source framework that turns any LLM‑based agent into a secure, identity‑verified, payment‑enabled internet service. It provides built‑in mTLS, DID signatures, OAuth2 via Hydra, USDC (x402) payment enforcement, skill advertising, push notifications, and polyglot SDKs (Python, TypeScript, Kotlin). With a single `bindufy()` call you get a JSON‑RPC endpoint, optional public tunneling, and deployment helpers, making it easy to build swarms, paid APIs, or regulated B2B agent integrations.

Torch-RecHub is a PyTorch framework for building recommender systems with 30+ models, modular design, ONNX export, and support for multiple hardware backends.

An embeddable, zero-dependency vector database for Go that enables RAG and semantic search without requiring a separate database server.

An integrated platform for building and hosting dynamic websites and web applications featuring a high-performance runtime and Native AI for automated site creation and maintenance.

A distributed caching platform that accelerates data-intensive analytics workloads by bridging the gap between computation frameworks and various storage systems.

A lightweight, privacy-focused LLM chat service that allows users to interact with AI models via HTTP, SSH, DNS, and an OpenAI-compatible API.

A Rust‑based, step‑by‑step course that guides you to implement an in‑memory vector database, covering Arrow tables, DataFusion integration, and several ANN indexes (IVFFlat, NSW, HNSW, IVF‑PQ), with SQL support and benchmark tools.

A set of skill definitions and tools for the Universal Agentic Registry, allowing AI assistants to discover, chat with, and register AI agents across multiple protocols.

A parallel coarse-to-fine motion planning framework for autonomous driving that uses discrete flow matching and GRPO to generate safe, command-following trajectories.

KouriChat is a Python chatbot that links LLM APIs (e.g., DeepSeek) to the OneBot messaging protocol, offering role‑play conversations, persistent memory, emoji‑styled replies, and a web UI. It runs on Windows, is configured via a `kourichat.toml` file, and is targeted at QQ groups and other OneBot‑compatible chats.

A Go-based TUI for real-time log analysis that combines live streaming, visual dashboards, and AI-powered insights for debugging distributed systems.

A financial market simulation engine powered by a generative foundation model that simulates individual order events to create realistic emergent market behavior.

A task management system designed for AI assistants that uses the Model Context Protocol (MCP) to enable AI agents to autonomously manage tasks and projects.

An MCP server that integrates Google Calendar with AI assistants, enabling them to manage schedules, detect cross-account conflicts, and create events from images or PDFs.