Trending AI projects

tts‑bench is a Python‑based benchmark suite for local text‑to‑speech models. It lets you install dozens of open‑source TTS systems, run them on CPU, CUDA or Apple‑Silicon, and compare speed (TTFA, realtime factor, memory), listen to generated audio (default voice and zero‑shot cloning) and view objective scores (UTMOS, WER, SIM). A public voting arena supplies human‑preference rankings for “best sounding” and “best cloning”.

Workflow Builder is an Apache‑2.0 React SDK that provides a drag‑and‑drop visual workflow editor. It ships with a plugin‑first architecture, a design‑system UI kit, and a reference back‑end (Hono + Temporal + Postgres) that can run AI‑agent nodes via any OpenAI‑compatible LLM. You can embed the SDK in minutes, try a browser‑only demo, or launch the full stack with Docker. Ideal for SaaS products, low‑code builders, or anyone needing a UI to design rule‑based or AI‑driven workflows.

A self-hosted code context layer that indexes multiple repositories for centralized code search and AI agent integration via MCP.

A collection of Python sample codes and documents providing a technical guide for beginners to learn autonomous vehicle control algorithms and software architectures.

ArcadeDB is a high-performance multi-model database that supports graph, document, key-value, time-series, vector, and geospatial data with multiple query languages and an MCP server for AI integration. It runs embedded or remotely via various drivers, offering ACID transactions and 70+ graph algorithms.

A cross‑platform command‑line interface for Higgsfield’s suite of generative AI models (image, video, 3D, audio) plus utilities for building React web apps, publishing browser games, and managing personal “Soul” avatars—all from the terminal.

Embedding Atlas is an interactive visualization tool for exploring large-scale embeddings and tabular data, offering automatic clustering, cross-filtering, and multimodal support for deep data analysis.

A scientific machine learning library for solving differential equations and learning operators using physics-informed neural networks and other advanced AI architectures.

D‑FINE is a real‑time object‑detection framework that redefines DETR’s box regression as a fine‑grained distribution refinement and adds a self‑distillation module. It offers several model sizes (‑N to ‑X) that achieve state‑of‑the‑art COCO/AP scores (42.8 %–55.8 %) while running at 70‑470 FPS on a T4 GPU, with no extra inference cost. The repo provides pretrained checkpoints, config files, and full training/evaluation scripts for COCO, Objects365, and custom COCO‑style datasets.

Pointcept is a modular, research-focused codebase that provides a unified framework for 3D point cloud perception, integrating state-of-the-art models, pre-training techniques, and standardized data processing pipelines.

A mobile AI gateway that runs a Linux environment on Android to enable AI agents to control device hardware like cameras, sensors, and location services.

A lightweight Rust-based proxy that turns Claude.ai and Claude Code into OpenAI-compatible API endpoints using session cookies.

An MCP server that enables AI assistants to launch, manage, and analyze Meta Ads campaigns across Facebook and Instagram through natural conversation.

A framework for building LLM-based agent simulations in urban environments and social science research workflows.

An AI-driven automation testing platform that uses LLMs and RAG to automatically generate, manage, and execute functional, API, and UI test cases from requirements.

AI-Meeting is an open-source backend for AI-powered mock interviews. It parses resumes, generates and scores interview questions via multiple AI agents, supports real-time speech transcription and long-text synthesis, and provides a full user and permission system. Built with Spring Boot 3 and Spring AI, it's designed for learning and for building practical job-prep platforms.

A C++ plugin for Godot 4 that provides Behavior Trees and Hierarchical State Machines to help developers create complex, modular AI behaviors for game agents.

Mirobody is a self-hosted AI health data engine that standardizes medical records, lab reports, and wearable data into a unified format, allowing users to query their health history with traceable citations.

An open-source API and RSS generator for WeChat Official Accounts that enables full-content scraping, multi-format archiving, and AI client integration via MCP.

A command-line tool that allows AI agents to securely make payments and access financial data on behalf of a user via their Link wallet.

Chaterm is an AI-native terminal that enables engineers to manage infrastructure and cloud resources using natural language, automating complex tasks like deployment and troubleshooting through an intelligent agent.

A framework that combines LLMs and evolutionary algorithms to automate the discovery and optimization of scientific code across various programming languages.

Ship Safe is an MIT‑licensed CLI that locally scans AI‑augmented codebases for classic and AI‑specific security issues, validates findings with data‑flow tracing and optional LLM analysis, and offers interactive fixing and CI integration.

A browser extension that provides instant translations of web text, images, and PDFs via tooltips using Google and Bing translation services.

A Rust-based text splitting library that breaks long documents into semantically sensible chunks for LLM context windows, supporting plain text, Markdown, and source code.

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

A Python library providing clean-room implementations of popular multi-object tracking algorithms that plugs directly into any detection model to handle occlusions and camera motion.

A 2D Gaussian Splatting implementation that uses oriented disks (surfels) to create geometrically accurate radiance fields and high-quality 3D meshes.

A local-first operating layer for AI-assisted game design that transforms fragmented AI output into structured, evidence-linked design decisions and project memory.

Arch Studio is a local‑first plugin for Codex and Claude Code that gives architecture firms a governance‑driven AI workflow layer. It ships with ready‑made AEC skills (spec‑writing, zoning, sustainability, FF&E, etc.) and specialist agents, lets firms create private studio‑ and project‑level skills, and stores all records locally in CSV files. The plugin is installable via each host’s marketplace and is fully open‑source under MIT.

Bespoke Curator is a Python library for bulk LLM inference and synthetic data generation. It provides a `curator.LLM` base class for prompt/parse logic, supports many providers (OpenAI, Anthropic, Gemini, Ollama, vLLM, etc.), offers batch mode and caching to cut costs, includes a code‑execution engine, and integrates with the Tinker SDK for LoRA fine‑tuning. Ideal for building large‑scale, structured datasets for training or evaluation.

A standalone, open-source AI coding agent with durable codebase memory, multi-agent orchestration, and a built-in toolbox for autonomous software development.

EcoLogits is a Python library that estimates the energy consumption and CO₂‑equivalent emissions of generative‑AI API calls (OpenAI, Anthropic, Cohere, Google‑GenAI, HuggingFace, Mistral AI, etc.). It wraps the provider’s client, looks up model‑specific emission factors, and attaches an `impacts` field to the response containing mean energy (kWh) and GWP (kg CO₂‑eq). Install via `pip install ecologits` (optionally with `[openai]` etc.), call `EcoLogits.init`, then use the provider as usual; the library returns the impact metrics alongside the normal response.

An open-source AI code reviewer that provides instant feedback on pull requests and local changes using any LLM provider.

CamoFox Browser Server is a TypeScript REST API that wraps the Camoufox stealth browser engine to provide anti-detection browser automation for AI agents. It eliminates the need for fragile JavaScript patches by moving fingerprint spoofing to the C++ engine level, and offers a REST API and CLI for programmatic control.

A local-first Kanban board that scales from simple task management to a governed, multi-agent orchestration platform for autonomous coding workflows.

An open-source MLOps and LLMOps suite that provides experiment tracking, orchestration, and data management to streamline the deep learning development lifecycle.

An agent skill that turns a topic into a short film or a playable NES-style game using programmatic visuals and synthesized audio instead of media assets.

An open-source, comprehensive guide to LLM data engineering that provides a systematic framework and 15 practical projects for managing data pipelines from pre-training to production.

A curated, categorized collection of academic papers and technical resources focused on the systems engineering behind Large Language Models, including training, serving, and agentic architectures.

A curated directory of open-source projects that automate the scientific research process, including literature review, experiment execution, and paper writing.

A Python package that adapts the Segment Anything Model (SAM) for geospatial data, enabling easy segmentation of satellite imagery using text, points, or boxes.

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

A curated collection of 573 Microsoft Copilot prompts for enterprise professionals, organized by role and function and checked against responsible AI guidance. It helps users get more from Microsoft 365 Copilot across Outlook, Excel, Word, Teams, and more.

A curated, open collection of Agent Skills for scientific research, covering bioinformatics, chemistry, data analysis, literature search, and more. It gathers high-quality, science-relevant skills from official and community sources into a clone-ready repository that works across multiple AI coding agents.

Zenith is a Python harness that lets Claude Code, Codex, or Hermes run as long‑running coding agents. An orchestrator repeatedly checks project state, spawns worker/tester sub‑agents, registers reusable skills, replans, and only stops when the task is truly complete. Benchmarked on the Frontier SWE suite, Zenith (using GPT‑5.5) achieves the best average rank while costing less than half of the strongest baseline (RALPH). The repo provides a CLI, MCP server, ACP adapters, and a full technical report.

A modular, data-driven research simulator for autonomous driving that enables closed-loop testing of end-to-end AV policies with high-fidelity sensor simulation.

A plugin for AI coding agents that provides direct access to Shopify documentation, API schema validation, and store management tools to streamline Shopify app and theme development.