Trending AI projects

An academic harness for AI agents that provides the structured evidence, library management, and repeatable workflows needed for professional research and academic writing.

An Unreal Engine 5-based simulation platform for developing and evaluating LLM/VLM agents in realistic physical and social environments.

An MCP server that gives AI agents free, keyless web search and anti-bot fetching capabilities, allowing them to bypass bot walls and crawl the web locally.

A Python package for probabilistic time series modeling that uses deep learning and PyTorch to generate forecasts with uncertainty intervals.

A recursive self-improvement harness that automates the process of running, evaluating, and refining AI agent strategies to create durable playbooks and datasets.

Company Research Agent is a FastAPI + React app that, given a company name, automatically searches the web (via Tavily), scores sources, and uses any OpenRouter‑compatible LLM (or OpenAI/Gemini) to produce a structured, source‑backed briefing, streamed live to the UI and exportable as PDF. Optional MongoDB persistence and Docker deployment are supported.

A comprehensive, community-maintained directory of tools, hardware, datasets, and educational resources for Brain-Computer Interface (BCI) research and development.

An AI-powered tool that automatically generates comprehensive Markdown READMEs, project logos, and interactive wikis for software repositories.

An agentic browser driver built in Rust that provides AI agents with a stealthy, token-efficient way to control a real browser via a persistent Live Page Model.

Metis is an open-source coding agent that runs as a desktop app, terminal tool, or Skill, letting each project define its own agent architecture. It automates planning, coding, review, and testing through editable workflows and automatic task tiers.

A free, open-source voice-to-text tool that allows you to dictate text into any application locally on your computer for maximum privacy.

HeartMuLa is an open-source family of music foundation models that enables high-fidelity music generation from lyrics and text tags, along with tools for audio codec reconstruction, lyric transcription, and cross-modal retrieval.

SmollM is Hugging Face’s open‑source family of tiny yet powerful models: SmolLM‑3 (a 3 B‑parameter, 128 k‑token, multilingual instruction model) and SmolVLM (a compact vision‑language model). All weights, data mixes, and training configs are public, and the models can be loaded with the standard `transformers` library for CPU or modest‑GPU inference.

TabArena is a standardized, living benchmarking system for tabular machine learning that provides a reliable, reproducible environment for evaluating models and AutoML systems across diverse datasets.

An AI-powered tool that automatically collects, recognizes, and organizes electronic invoices from emails into categorized folders and Excel reports for reimbursement.

A serverless Python runtime and client library for deploying and scaling ML models and pipelines in the cloud without managing infrastructure.

The open-source platform for sharing and collaborating on Stable Diffusion models, featuring a community-driven repository for model discovery and development.

Surf is a command-line tool that lets AI agents control Chrome via simple commands and a browser extension, offering zero config, agent-agnostic use, and the ability to query AI services without API keys.

A multi-agent AI system that simulates a professional investment research institution to provide deep analysis and trading suggestions for the A-share market.

A curated collection of 30 runnable Jupyter notebooks that teach every major memory pattern for LLM agents—from short‑term buffers to long‑term vector stores, knowledge graphs, and production‑grade frameworks (Mem0, Letta, Zep, Graphiti). Organized into six families, the repo provides hands‑on code, comparison tables, and a decision tree to help developers choose and implement the right memory technique for their AI agents.

An open-source, AI-powered presentation generator that creates customizable slides from a topic via an outline-first workflow.

A comprehensive training suite for diffusion models that provides tools for dataset preparation, fine-tuning, and model conversion through a GUI or CLI.

An open-source, self-hosted dashboard that tracks brand visibility and performance across major AI search engines like ChatGPT and Gemini. It helps marketers analyze citations, sentiment, and search optimization without relying on expensive third-party SaaS platforms.

Research Toolkit is a framework of methods and tools that helps AI agents produce evidence-based, traceable research reports with built-in review and revision workflows.

InternalBeyond-Mobile is a single-file, local-first PWA that turns your phone into a private AI companion hub: multiple AI assistants each keep their own long-term memory of you, all your data stays in the browser, and you can import ChatGPT/Claude histories to continue old conversations. It covers chat, calls, letters, diary, calendar, music, co-reading, map journeys and more, all without any server.

VMAF is an Emmy-winning perceptual video quality assessment algorithm that helps developers accurately measure and optimize video quality for streaming and compression.

A knowledge graph database with built-in version control that allows users to manage, collaborate on, and query linked JSON data using a git-like model.

A library for approximate convex decomposition of 3D meshes, enabling efficient collision detection by breaking complex shapes into a small number of convex components.

A DOCX-native document engine that allows for browser-based editing and programmatic automation via a unified API, specifically designed to be agent-ready.

An open-source, local-first workspace that allows humans and multiple AI coding agents to collaborate via channels, threaded task boards, and shared memory.

A WebAssembly binding for llama.cpp that enables running LLMs, multimodal models, and tool calling directly in the browser via WebGPU or Wasm SIMD.

AutoRound is an open‑source Python toolkit for post‑training quantization of large language and vision‑language models. It supports ultra‑low‑bit (2‑7 bits) and mixed‑precision schemes, integrates with Transformers/vLLM/SGLang, and runs on Intel CPUs/XPUs, NVIDIA GPUs, and Habana Gaudi. Users can quantize via a simple CLI or Python API, choosing recipes that trade speed for accuracy, and export to formats like GGUF for downstream inference.

A PyTorch-based library for time series forecasting that provides a high-level API and state-of-the-art deep learning architectures like Temporal Fusion Transformers and N-BEATS.

pi-fabric is a programmable runtime for the Pi coding agent that lets you write one TypeScript or Python program to coordinate tools, MCP servers, agents, actors, and workflows, with guardrails and a live dashboard.

KubeRay is a CNCF‑sandbox Kubernetes operator that adds custom resources (RayCluster, RayJob, RayService) for declaratively running Ray‑based AI/ML workloads—training, inference, and serving—on any Kubernetes cluster, with built‑in autoscaling, fault tolerance, and optional UI/CLI tools.

A library of portable Markdown persona files (SOUL.md) that give AI agents distinct identities and behavioral convictions to move beyond generic assistant voices.

AIMM is a Python tool that logs into Facebook Marketplace, searches for user‑defined items, uses an LLM to rate each listing, and sends instant notifications via many channels. It offers a CLI, an AI‑guided configuration wizard, a local web UI, and Docker/NAS deployment options.

A design system framework for AI coding agents that enforces consistent UI development through a structured, machine-verifiable DESIGN.md contract and automated quality gates.

An open-source project providing full hardware and firmware designs for high-performance brushless servo actuators used in robotics.

A comprehensive AstrBot plugin that analyzes group chat activity to generate visual reports, topic summaries, and AI-generated comics.

SuggestArr is an open‑source Docker‑based service that reads watch history from Jellyfin, Plex or Emby, generates AI or TMDb‑based recommendations, and automatically creates download requests in Seer. It supports LLMs, Trakt sync, public‑list imports, filtering, cleanup jobs, a web UI, and a public Swagger‑documented API.

A toolkit for training neural networks to model the behavior of guitar amplifiers and audio equipment, exporting them for real-time use.

A Calibre plugin that translates ebooks into specified languages using various translation engines like ChatGPT, Gemini, and DeepL.

Maid is an open‑source Android app (React Native) that lets you run GGUF LLMs locally via llama.cpp or connect to many remote LLM providers. It offers one‑tap model downloads, chat management, adjustable generation parameters, theming, and optional text‑to‑speech via the companion Maise app.

A runtime substrate for AI agents that provides secure sandboxing, reversible execution traces, and a review-and-approve workflow for all filesystem changes.

An LLM API aggregation service that unifies multiple AI providers into a single interface with protocol conversion and automatic failover.

An open-source multi-agent AI assistant that allows users to build autonomous AI teams and companies to execute complex tasks across desktop, web, and mobile platforms.

A collection of 14 installable skills for AI coding agents that help developers identify requirements gaps and technical unknowns before implementation.