A file-backed workflow and runtime for AI agents that replaces chat memory with repository-local artifacts to ensure continuity and consistency across sessions.

A Chrome extension that adds a native AI layer to the browser, integrating multiple LLM providers and enabling agentic browser control and external MCP tool support.

A structural code navigation tool and MCP server that helps AI agents read codebases more efficiently by providing outlines, definition-first search, and call-chain tracing.

A security scanning tool for Model Context Protocol (MCP) servers and tools that uses YARA, LLMs, and Cisco AI Defense to detect malicious behavior and vulnerabilities.

An open-source mobile app for Android and iOS that enables private, on-device LLM chat, image generation, and video generation using hardware acceleration.

A high-performance job queue for Bun that replaces Redis with SQLite or PostgreSQL, featuring a built-in workflow engine and native MCP support for AI agents.

A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.

A self-improvement plugin for Claude Code, Codex, and OpenCode that turns user corrections and successful interactions into durable, reusable skills and rules.

A starter template for building AI chat agents on Cloudflare, featuring integrated tool-calling, task scheduling, and vision capabilities powered by the Agents SDK.

A Node.js library that provides pre-built bindings for llama.cpp, enabling developers to run LLMs locally with automatic hardware acceleration and TypeScript support.

An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

A molecular design tool that uses reinforcement learning and transfer learning to generate optimized small molecules based on user-defined property profiles.

Helios is a 14B parameter real-time long video generation model capable of producing minute-scale, high-quality videos at up to 19.5 FPS on a single H100 GPU.

MAGI-1 is an autoregressive video generation model that produces high-fidelity videos chunk-by-chunk to ensure temporal consistency and physical accuracy.

A high-performance automatic differentiation plugin for LLVM and MLIR that synthesizes fast gradients for optimized code, including GPU kernels and parallel programs.

An in-memory platform for distributed, scalable machine learning that provides a wide range of algorithms and an AutoML feature for automated model building.

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

A Python library for user-friendly time series forecasting and anomaly detection, offering a unified API for models ranging from classic statistical methods to deep neural networks.

Chorus is a management harness for AI coding agents that implements the AI-DLC workflow, allowing teams to orchestrate multiple agents and ensure human verification of AI-proposed code.

An AI-powered omnichannel customer service platform that integrates AI agents, RAG, and multi-channel communication to streamline business-customer interactions.

The official Neo4j Python package for building GraphRAG applications, enabling the automated construction of knowledge graphs and hybrid retrieval for LLMs.

EdgeQuake is a Rust‑based Graph‑RAG system that converts PDFs/TXTs/MDs into an entity‑relationship knowledge graph, stores both graph data (Apache AGE) and embeddings (pgvector), and answers queries by combining vector search with graph traversal. It ships as multi‑arch Docker images, includes a React UI, supports many LLM providers, and offers production‑ready features like multi‑tenant auth, migrations, and health checks.

A collection of reference implementations and tutorials for building generative AI systems, RAG pipelines, and agentic workflows using the NVIDIA software ecosystem and NIM microservices.

Dust is a custom AI agent platform that allows users to create specialized AI agents to speed up their professional work.

A Python library for building scalable synthetic data pipelines, providing bulk inference and structured output tools to curate high-quality datasets for post-training.

An open-source AI orchestration framework that implements an agentic agile workflow to prevent context loss and planning inconsistency in AI-assisted software development.

Ludwig is a declarative deep learning framework that enables users to train, fine-tune, and deploy LLMs, multimodal, and tabular AI models using YAML configuration files instead of boilerplate Python code.

A portable, single-file memory layer for AI agents that provides persistent long-term memory and instant retrieval without requiring a database.

An open-source, self-hosted platform for tracking and optimizing brand visibility and citations across AI answer engines like ChatGPT, Perplexity, and Gemini.

A collection of enhancements, plugins, and prompts for OpenWebUI that adds autonomous agent capabilities, data visualization tools, and context optimization.

A JSON-based interface for ROS that allows external clients to publish, subscribe, and call services via WebSockets or TCP.

A lightweight Python-based 3D eye tracking algorithm that detects the pupil ellipse from video or image data.

A developer UI for the Google Agent Development Kit that simplifies the building, debugging, and orchestration of AI agents.

An Android app that uses machine learning to identify over 6,000 bird species by their sound in real time and entirely offline.

A benchmark for evaluating LLMs on real-world enterprise text-to-SQL workflows across multiple SQL dialects and complex data environments.

An agentic AI security framework for deep security code review that uses LLMs to detect subtle vulnerabilities and reduce false positives through integrated triage.

A codebase knowledge graph tool that indexes structural dependencies and exposes them via a visual dashboard and MCP tools for AI agents.

An AI-powered job hunting assistant that automates resume submission and HR communication on Boss Zhipin using LLMs to act as a candidate's digital twin.

An open-source web application for AI model security assessments that uses probes to test for vulnerabilities and jailbreaks before deployment.

A graph deep learning library for materials science that provides various GNN architectures to predict material properties and simulate potential energy surfaces.

A free, lightweight desktop application that provides a unified interface for interacting with multiple LLM providers and local models using your own API keys.

A self-hosted universal LLM API proxy that provides OpenAI and Anthropic compatible endpoints for multiple providers with built-in key rotation and failover.

An automated transaction categorization tool for Actual Budget that uses LLMs to integrate with various AI providers to classify expenses and suggest new categories.

TAEHV is a tiny auto‑encoder that speeds up and memory‑optimizes video VAE decoding for many diffusion models (Hunyuan, MiniMax‑H3, Wan‑Video, CogVideoX, Open‑Sora, LTX‑2, etc.). It reduces decoding of a 61‑frame 512×320 clip from ~2‑3 s / 6‑9 GB to ~0.5 s / <0.5 GB, with a small quality trade‑off. The repo ships model checkpoints, Python API (`TAEHV`, `StreamingTAEHV`), example notebooks, and integration notes for ComfyUI, stable‑diffusion.cpp, SDNext, and Diffusers.

torch_musa is a PyTorch extension that adds a **MUSA** backend for Moore Threads GPUs. It mirrors the standard PyTorch API, so you only replace `cuda` with `musa`. The package includes tools for building C/C++ extensions, distributed training via the **mccl** backend, and Docker images for easy setup. It also provides MUSA‑compatible builds of torchvision, torchaudio, and a curated list of other popular PyTorch libraries. Installation can be done from pre‑built wheels or by building from source after installing the MUSA SDK. The project is BSD‑licensed.

A PyTorch implementation of Rectified Flow and its variants, enabling more efficient generative modeling by straightening the paths between noise and data.

AIDA is an open‑source autonomous pentesting platform that lets any LLM (Claude, Gemini, OpenAI, etc.) drive a Docker‑based security‑testing environment. The agent can run reconnaissance, scanning, custom Python exploits, and raw HTTP manipulations, logging every command and its output in a persistent notebook. Findings are auto‑scored with CVSS 4.0 and can be exported as PDF reports. The project includes a web dashboard, JWT authentication, notification hooks, and supports swapping the built‑in `aida-pentest` container for the larger Exegol image. Real CVEs discovered by AIDA are listed, showing practical impact. Licensed under AGPL‑v3.

A deployment framework for running a persistent, 24/7 Claude Code agent with a real browser on your own VPS, controllable via Telegram.