A free, open-source application for local audio transcription and speaker identification, designed for researchers and journalists to ensure data privacy.

A local-first knowledge management system that captures, indexes, and makes searchable all interactions with AI coding assistants across various IDEs and CLI tools.

A lightweight framework for building autonomous agents capable of deep research, code generation, and multimodal tasks using a knowledge-driven skill system.

A resilient, tightly-coupled multi-sensor SLAM framework that maintains accurate localization for wheeled, legged, and aerial robots even during sensor degradation or calibration errors.

NavDP is an end-to-end mapless navigation model using diffusion policies that enables robots to perform real-time path planning and obstacle avoidance with cross-embodiment generalization from simulation to reality.

A persistent, simulated world where autonomous AI agents with unique personalities and memories build societies, govern themselves, and evolve over time to study emergent behaviors.

A Windows desktop assistant that provides cursor-side input method status indicators and programmable AI-powered hotkeys for translation and productivity.

A collection of tutorials and reference implementations for AgentKit, an enterprise AI Agent platform, covering everything from basic dialogue to complex multi-agent systems and RAG.

A Windows facial recognition unlock tool that uses OpenCV and a custom Credential Provider to enable face-unlock capabilities on devices without native Windows Hello hardware.

A collection of utilities, notebooks, and serving components for working with IBM's Granite Time Series Foundation Models for forecasting.

Isaac Lab‑Arena is an alpha‑stage, open‑source extension to NVIDIA Isaac Lab that lets you build robot simulation environments by mixing reusable *scene*, *embodiment*, and *task* primitives. It assembles these at runtime, supports sequential task chaining, natural‑language object placement, and large‑scale parallel evaluation, making it easier to benchmark or train generalist robot policies. Installation works via the `uv` Python manager or a provided Docker image; the library is Linux‑only and requires an NVIDIA GPU and Isaac Sim. The project is under Apache 2.0 (with proprietary Isaac Sim components) and is intended for research rather than production.

An iOS and macOS Markdown renderer optimized for LLM streaming, providing smooth transitions, LaTeX support, and inline citation UI.

A lightweight, header-only message marshalling library for efficient communication between drones and ground control stations.

GeoCalib is a research‑grade Python library that predicts camera intrinsics and scene gravity from a single image using a deep network plus geometric optimisation. It supports multiple lens models, partial priors, batch and multi‑camera rig calibration, and ships with easy‑install inference code, a Gradio web demo, a Colab notebook, and a live webcam demo. Pre‑trained models are trained on the OpenPano dataset (≈37 k perspective crops from HDR panoramas) and achieve state‑of‑the‑art results on benchmarks such as LaMAR, MegaDepth, TartanAir, and Stanford2D3D.

A production-grade Sanskrit chant text-to-speech system that generates traditional melodic recitation instead of flat read-aloud speech.

An open-source eye-tracking library that enables eye-driven interfaces using standard webcams and phone cameras instead of expensive specialized hardware.

A fast and sensitive tool for comparing and clustering large protein structure sets, supporting both monomer and multimer searches with GPU acceleration.

bioSkills is a library of ready‑made code templates (“skills”) that teach LLM coding agents how to perform bioinformatics analyses—from sequence I/O to single‑cell, variant calling, structural biology, chemoinformatics, and workflow management. Installable via thin scripts for Claude Code, Codex, Gemini/Antigravity, OpenCode, and OpenClaw, the skills provide best‑practice command‑line flags, example scripts and usage guides, improving the correctness of AI‑generated bio‑informatics code.

A PyTorch-based library for Bayesian Optimization that provides a modular framework for composing probabilistic models and acquisition functions.

A Python library for converting PyTorch models into .tflite format, enabling high-performance on-device execution on Android, iOS, and IoT devices.

A collection of pipelines for LLM development that streamlines synthetic data generation, training, and evaluation across local workstations and large-scale GPU clusters.

Vestige is an open‑source, locally‑run memory layer for LLM coding agents. It records decisions as “memories”, merges duplicates, flags contradictions, and can backtrack from a bug to the earlier decision that caused it (backfill). All data stays on the developer’s machine (SQLite), with optional encrypted sync via a paid Pro tier. Installation is a single npm command; the tool ships as a 25 MB Rust binary that downloads an embedder and reranker once, then works offline. Benchmarks show Vestige helping agents converge on correct fixes far more reliably than plain vector‑search RAG. Licensed under AGPL‑3.0.

A production-tested AI agent harness that implements SAFe methodology to coordinate multi-agent teams across various AI providers like Claude and Gemini.

A professional context and harness engineering system that wraps around Claude Code and Codex to provide durable context, quality gates, and runtime verification for production-grade software.

VLM-R1 is a framework for training R1-style Large Vision-Language Models using GRPO to improve reasoning and generalization in tasks like visual grounding, math, and object detection.

A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for concurrent development.

The official JavaScript/TypeScript SDK for LM Studio, enabling developers to integrate local LLMs into applications with advanced memory and hardware controls.

An OCR tool specifically optimized for Japanese manga, capable of recognizing multi-line text, furigana, and both vertical and horizontal layouts.

OmniLottie is a multimodal AI generator that creates complex vector Lottie animations from text, image, or video inputs using pre-trained Vision-Language Models.

A deep probabilistic programming library built on PyTorch that allows users to create and scale universal probabilistic models for large datasets.

MemoryOS is a memory management system for AI agents that uses a hierarchical storage architecture to maintain short, mid, and long-term personalized memory for more coherent interactions.

An open-source engine that adds a persistent learning loop to AI agents, allowing them to learn from mistakes and improve via a dynamic 'Skillbook' of strategies without fine-tuning.

A collection of public AI agent skills that extend agent capabilities with tools for dynamic workflows, Claude Code plugin development, and personalized learning.

A template for building AI-driven workflow automation platforms, featuring a visual drag-and-drop builder that generates executable TypeScript code.

An open-source self-hosted ML platform that combines an AutoML engine, a control plane for experiment management, and a web UI for a complete train-to-deploy workflow.

A command-line tool for agentic document extraction that converts complex documents into grounded Markdown and structured data with verifiable evidence.

A self-hosted AI agent that runs locally on your machine, providing a native desktop app and integration with multiple messaging platforms like Discord and Slack.

A macOS menu bar app that provides live status indicators for Claude Code, showing whether the AI is working, thinking, or awaiting user permission.

A portability layer and operation set for ML models that enables interoperability between different ML frameworks and ML compilers.

A community repository providing the core image generation, sampling, and training code for the Draw Things app, including a self-hostable gRPC server for remote inference.

A diffusion-based framework for high-quality singing voice synthesis and text-to-speech generation from lyrics, MIDI, and pitch data.

GraphRAG‑SDK is a Python SDK that builds a knowledge graph in FalkorDB from your documents and then answers questions by traversing that graph. It adds provenance edges, multi‑hop retrieval, and optional abstention to dramatically cut down LLM hallucinations, and it ships with benchmarks showing it outperforms standard vector‑RAG. Install via pip, run a FalkorDB container, ingest texts (or PDFs/markdown), call `finalize()`, and query with `completion()`. The library supports schemas, incremental updates, custom providers, and is Apache‑2.0 licensed.

A browser-based robot teleoperation platform that crowdsources human demonstration data for training Vision-Language-Action (VLA) models and imitation learning policies.

A platform-agnostic website specification that consolidates fragmented web standards into a single reference, including tools to make sites legible to AI agents.

A full-stack SaaS boilerplate using Fastify, React, and tRPC that provides a pre-configured foundation for building AI-powered web applications with OpenAI integration.

An LLM-assisted utility for PID tuning that analyzes system responses from hardware or simulations to automatically suggest and apply optimal control parameters.

FlashRAG is a Python library that provides a modular framework, benchmark datasets, and implementations of 23 SOTA Retrieval‑Augmented Generation (RAG) methods (including reasoning‑based and multimodal approaches). It supports dense, sparse, and neural‑sparse retrieval, fast LLM inference via vLLM, and offers a web UI for easy configuration and evaluation.

An offline voice recognition input method for Android based on the Whisper engine, providing privacy-focused speech-to-text and translation.