Trending AI projects

Banana Claude is a plugin that plans, reviews, and executes Google Gemini image‑generation requests, giving users a safe, cost‑controlled workflow for creating, editing, comparing and typesetting AI‑generated visuals.

The OpenAI CLI is an official command-line tool that allows users to interact with the OpenAI REST API directly from their terminal, enabling tasks like image generation, file management, and batch processing without writing custom code.

A high-performance, lightweight IDE built specifically for reviewing AI-generated code, featuring native Git/GitHub integration and seamless handoff to AI coding harnesses.

A high-performance code-intelligence engine that indexes codebases into knowledge graphs to provide AI agents with precise context, reducing token usage by up to 50x.

A static, open-source collection of modular NSFW prompt templates for AI agents, organized into 14 ordered modules with 35+ themes and 200+ poses, plus a fixed assembly formula to produce detailed English prompts for adult image generation. It targets AI models like DeepSeek Flash and includes best practices for consistency and quality.

A ComfyUI custom node that provides an interactive 3D viewport for controlling camera angles and generating compatible prompts for the Qwen-Image-Edit-2511-Multiple-Angles-LoRA.

Row‑Bot is a self‑hosted desktop AI assistant that lets you converse with LLMs to create files, run code, manage designs, and interact with services—all while keeping data locally. It offers memory via a personal knowledge graph, goal‑driven agents, approval‑gated actions, multi‑device remote access, and integrations (GitHub, Notion, Slack, etc.). Runs on Windows/macOS/Linux or Docker, using Ollama or any OpenAI‑compatible provider, and stores everything securely on your machine.

Grok App is an open‑source desktop workbench (macOS/Windows/Linux) that provides a GUI for the local Grok Build CLI. It offers multi‑project workspaces, real‑time streaming of agent reasoning, file editing with live sync, Git integration, omnichannel IM bridges, and customizable UI, all while keeping the LLM execution local.

Genex is a desktop app for game development with AI, letting you use chat-based agents (from Claude Code, ChatGPT, or local models) as a multi-agent team to create assets, code, and entire games, with export, publishing, and plugin extensibility.

A curated GitHub list of generative AI projects and services, organized by category (text, coding, image, audio, etc.), with recommended reading, milestone announcements, and community-contributed links.

A specialized subtitle generator for Japanese Adult Videos that uses a hardened pipeline of VAD, scene detection, and post-processing to prevent hallucinations and improve accuracy in noisy audio.

A high-performance structured data engine for .NET that uses a compact token-based intermediate representation to accelerate serialization, deserialization, and in-place editing across multiple data formats.

Agent Deck is a terminal-based command center that helps developers manage, monitor, and orchestrate multiple AI coding agent sessions from a single interface.

A CLI bridge that lets AI agents programmatically control Cadence Virtuoso and Spectre chip-design tools locally or via SSH, using Python, SKILL, or the command line.

EvoFlow is a native runtime and control‑plane for collaborative AI agents, enabling planning, execution, recovery, and delivery of long‑running tasks with observable, sandboxed workflows. It offers chat‑driven planning, multi‑agent teams, automation, code‑indexing, self‑evolution, governance tools, and a marketplace for extensions. Available as desktop apps (Windows/macOS/Linux) or from source, it is released under a source‑available non‑commercial license.

A structured research workflow for Claude Code, OpenCode, and Codex that enables systematic outline generation, deep web investigation, and automated report creation.

SocialCoach is an AI-powered social-skills practice tool that lets you rehearse tricky conversations (like asking for a raise or declining extra work), then review your performance with feedback based on your own words. It personalizes practice scenarios from 58 situations across 7 life categories and supports both Chinese and English.

A framework for AI agents to perform high-fidelity, verifiable website reconstruction by treating source sites as technical specifications and using automated multi-layer validation.

Open CoDesign is an MIT-licensed desktop app that turns plain-language prompts into polished, runnable artifacts like website prototypes, slide decks, and marketing assets. It runs fully on your laptop and works with any AI model you already pay for — Claude, GPT, Gemini, Ollama, or any OpenAI-compatible endpoint — so there is no cloud lock-in and no forced subscription.

An open-source operations platform for building AI agents, apps, and automations to streamline business processes and internal operations.

A vetted community marketplace for plugins that extend the capabilities of Claude Cowork and Claude Code.

A library of React components for building professional software product demo videos using Remotion, featuring specialized shots for AI interfaces and terminal sessions.

A structured multi-perspective deliberation framework that uses diverse AI personas to challenge assumptions and reach high-stakes decisions through adversarial reasoning.

whichllm is a CLI that detects your hardware (or a simulated GPU) and ranks Hugging Face LLMs that will actually run locally, using live benchmark data, memory‑fit estimates and speed predictions. It can output tables, Markdown, JSON, start a chat, or generate Python snippets, and includes planning commands for hardware upgrades.

A local-first issue board that integrates into the Codex AI agent, allowing the AI to autonomously track and update project tasks.

An Android app that translates text, images and documents entirely offline using on‑device ML models (Mozilla translation, PaddleOCR, CLD2, various TTS engines). Supports 55 languages, offers dictionary lookup, and provides an AIDL API for other apps. Install via F‑Droid; language packs are downloadable once for perpetual offline use.

A cross-platform mobile and desktop application that runs uncensored, open-source AI models locally on your device with no cloud dependency or content restrictions.

A DIY toolkit for Flipper Zero (and ESP32) that interacts with Tesla's CAN bus to unlock FSD features, bypass nag warnings, restore banned features, and provide live diagnostics, as a free alternative to commercial devices.

A standalone system that automates AI video production via Google Flow, using a Chrome extension bridge to handle authentication and a pipeline for maintaining visual consistency across scenes.

A deep learning library built on PyTorch that provides high-level components for rapid productivity and low-level components for research flexibility.

A local OpenAI-compatible API proxy that lets you use your DeepSeek Web Chat account as an API endpoint for tools like Open WebUI and Claude Code.

A comprehensive library of modular AI Agent skills for Codex and Claude Code, specializing in automated content creation pipelines for video, social media, and business analysis.

A harness‑neutral Agent Skill that lets an AI coding assistant generate a full‑length explainer video—either with a digital‑human presenter or in one of twelve animated styles—starting from a short topic or script. It orchestrates script writing, voice synthesis, presenter video, lip‑sync, captions, graphics, QA, and final rendering, all with evidence‑gated steps, cost guardrails, and provider‑agnostic support.

An open-source multi-agent framework for simulating large-scale agent societies to study scaling laws, emergent behaviors, and synthetic data generation.

A native Go-based MCP server that allows AI agents to directly interact with and manage Kubernetes and OpenShift clusters, replacing the need for manual CLI tool usage.

A curated, frequently updated directory of free-tier AI APIs, coding copilots, and infrastructure tools designed to help developers build production-ready AI applications without high monthly costs.

A family of pretrained foundation models for zero-shot time series forecasting that treats time series data as tokens for language model architectures.

A versatile CLI tool and browser extension that extracts and summarizes content from web pages, documents, and media files using various LLM providers.

ThoughtDAG is an open‑source desktop/web app that turns each LLM chat turn into a node on an infinite canvas. By connecting or disconnecting nodes (wires) you decide exactly which past turns become context for the next request, enabling branching, pruning, and merging of conversations. It includes a local index for searching past sessions, an optional Jev decision model for relevance ranking, a CLI for quick look‑ups, and a DeepSeek Harness plugin. Install via Homebrew, npm, or from source; configure any OpenAI‑compatible or Ollama endpoint. Features include document side‑by‑side clipping, condensing/weaving of paths, per‑node model selection, export of the graph as a “Thought Map”, and read‑only sharing. MIT‑licensed and actively maintained.

A local, privacy-focused tool that visualizes and replays the activity logs of AI coding agents, helping you audit what they read, edited, and where they encountered errors.

A web extraction tool that converts websites into clean Markdown, JSON, and LLM-ready context for use in AI agents and RAG pipelines.

An open-source desktop application that uses AI to automate the creation, management, and risk checking of professional bid documents.

An LLM-powered framework for creating intelligent Minecraft agents that can perform tasks, communicate, and execute code to interact with the game world.

OpenAdapt is an open‑source Python engine that records a human’s UI interaction (desktop, web, RDP, Citrix), compiles it into a repeatable program, and then **verifies** that the data entered into the target system was saved correctly by reading the record back through an independent channel. If verification fails, the run halts and a human is prompted. It supports multiple surfaces, policy‑driven certification, privacy‑first data handling, and can be run locally or via a managed cloud service.

A series of open-weight large language models (Qwen3.5, 3.6, and 3.8) that provide high-performance capabilities in coding, professional research, and autonomous agentic tasks.

AI Novel Generator is a self‑hosted web app that assists writers in planning and drafting novels using large language models. It provides Snowflake‑style hierarchical story planning (volumes → arcs → scenes → chapters), entity management (characters, factions, locations), a chapter editor with revision history, and a node‑based AI workflow designer. The stack includes Next.js front‑end, FastAPI back‑end, MongoDB storage, and adapters for OpenAI, Gemini, Claude, DeepSeek, etc. Users configure their own model API keys, run built‑in workflows to generate outlines and prose, edit the output locally, and keep all data private. Installation requires Python 3.13+, Node 20+, and a MongoDB replica set (Docker optional). Licensed under AGPL‑v3.

PDF Craft is a Python library that OCR‑extracts scanned PDFs, preserving structure (chapters, tables, footnotes, images) and exports the result as editable Markdown or EPUB. It supports remote or local DeepSeek‑based OCR, optional translation via a text LLM, and can write translated text back into a new PDF. The package offers synchronous and async APIs, reusable extraction files (.pcex), and an online demo for quick testing.

A Model Context Protocol server that turns Figma design systems into an API, enabling AI assistants to create designs, sync tokens, and audit design-code parity.