Trending AI projects

An open‑source guide and starter kit that turns an Obsidian vault into a personal “second brain” automatically curated by a Claude Code LLM agent. It provides a vault template, 18 LLM‑driven skills, 72 slash commands, scheduled sub‑agents, and detailed docs covering setup, ingestion, graph handling, and maintenance.

StemDeck is a local, open-source application that uses AI to split songs into individual instrument stems for practice and study without uploading your audio to the cloud.

An MCP server that integrates Firecrawl's web scraping and search capabilities into AI agents, enabling them to search, scrape, and interact with the live web for real-time context.

speech‑to‑speech is an open‑source Python toolkit that runs a full voice‑assistant locally. It chains VAD → speech‑to‑text → LLM → text‑to‑speech, with many interchangeable model back‑ends, and speaks the OpenAI Realtime protocol so existing clients can connect to your own machine.

F5-TTS is a high-performance text-to-speech system using a Diffusion Transformer and flow matching to generate fluent, faithful speech with fast training and inference.

OMX is a workflow orchestration layer for the OpenAI Codex CLI that adds structured planning, persistent state management, and multi-goal execution capabilities to improve developer productivity.

A third-party API integration library for XianYu that enables the creation of AI customer service agents by providing stable message communication capabilities.

awesome-jev is a curated list of public projects and practices built on Jev, TypeSafe AI's model for typed decisions (choice, score, boolean) with confidence. It organizes entries by application domain, requires public, citable, genuinely Jev-based examples, and explicitly warns that inclusion is not endorsement — no quality or security review is done.

RF‑DETR is an open‑source, transformer‑based library for real‑time object detection, instance segmentation, and keypoint detection. Built on a DINOv2 backbone, it offers a family of models (from tiny “Atto” to large “2XL”) that achieve state‑of‑the‑art COCO accuracy while running in 1–17 ms on an NVIDIA T4. Install via `pip install rfdetr`, use a single Python API for all three tasks, and optionally run NAS on the Roboflow platform to tailor a model to your own dataset.

delegate‑skills lets you discover installed AI coding‑assistant CLIs, group them into named lanes, and dispatch tasks to them via a uniform, review‑first workflow. It provides a setup skill to auto‑create a fleet configuration and per‑implementer delegate skills that run the chosen CLI head‑lessly, capture a diff and a structured result, and never commit automatically.

A reference implementation of AI shopping and merchant agents built on Claude, providing frameworks for customer-facing commerce and secure back-office management.

OpenLess is an open-source, cross-platform voice dictation app. Hold a hotkey, speak, and it uses your choice of ASR and LLM providers to transcribe and AI-polish your speech, inserting clean text directly at your cursor—with a special mode that turns rambling speech into structured prompts for ChatGPT/Claude. It's a privacy-focused, bring-your-own-keys alternative to Wispr Flow or Superwhisper.

OpenScience is an open‑source AI research workbench that lets users describe scientific tasks in plain language. The built‑in agent plans, searches literature, writes and runs code (Python/R/shell), executes experiments on local or remote compute, and produces a reproducible report, with every step logged. Available as a desktop app, web workspace, or CLI, it supports custom LLMs, a large library of domain‑specific skills, and extensible plugins.

Dolt is a MySQL‑compatible SQL database that adds Git‑style version control to tables. You can fork, branch, merge, and commit data using familiar Git commands or SQL system tables, enabling collaborative, time‑travel‑ready data workflows—useful for analytics, reproducible research, and AI agent memory.

A local dashboard and analytics tool that aggregates, searches, and tracks costs for various AI coding agents, keeping your session data private on your own machine.

An AI productivity environment that lets users create and run sandboxed, AI-generated mini-apps called Gadgets, managed by a capability-based security framework called Gatekeepers.

Spectrum‑ts is a TypeScript SDK for building AI agents that operate over real‑world messaging channels (iMessage, SMS, email, Slack, Telegram, etc.). It provides a unified, async‑iterator API, built‑in providers for major platforms, optional hosted infrastructure, and graceful startup cancellation. Install with `bun add spectrum-ts`, supply a Photon project ID/secret, and write a simple loop that replies to incoming messages.

A native iOS client for Hermes Agent that provides a secure, direct interface to your self-hosted AI agents with support for chat, voice, and remote dashboard management.

Claude Scholar is an open‑source, MIT‑licensed extension for Claude Code (and similar CLIs) that bundles dozens of ready‑made “skills”, agents, hooks and rules to help computer‑science/AI researchers automate literature handling, experiment tracking, analysis, and paper writing while keeping human decisions central. It integrates with Zotero and Obsidian, offers a full‑install script, selective install options, and a marketplace plugin.

Mesh2Motion is an open-source web application that allows users to import 3D models, assign skeletons, and apply animations for export, serving as a flexible, community-driven alternative to tools like Mixamo.

A local knowledge graph engine that gives AI coding agents persistent, context-aware memory by automatically injecting relevant project rules, code structure, and decision history into their workflow.

Official Python SDK for OpenAI’s API, offering sync/async clients, type‑safe request/response models, streaming, vision, realtime audio, and flexible authentication (API keys, workload‑identity, X.509).

An all-in-one video subtitle tool that uses LLMs for speech recognition, subtitle optimization, and translation to automate the video captioning process.

A curated collection of AI-generated motion works, gathering over 1,400 animations created by AI-written code (using tools like Blender, Three.js, Canvas) into a searchable, playable gallery with categories, source links, and prompts.

A collection of 157 AI agent skills providing specialized e-commerce expertise for sellers on Amazon, Shopify, eBay, and other major platforms.

AgenticSeek is an open‑source, fully‑local AI assistant that can browse the web, write and run code, and plan multi‑step tasks. It runs on your hardware (via Ollama, LM‑Studio, or similar) and stores all data locally, with optional voice interaction and a web UI.

A local AI creative studio and video editor that combines LLM-directed production workflows with image, video, and audio generation tools.

Codewhale is an open-source terminal-based coding agent that automates repository tasks, file editing, and command execution using a wide range of AI models.

A plugin for DeepSeek Harness that enables an AI agent to create, edit, and manage office documents like spreadsheets, presentations, and reports using natural language.

GPUStack is an open-source GPU cluster manager that orchestrates AI model serving and GPU instance provisioning across diverse infrastructure environments.

Skill Scanner is a Python‑based security scanner for AI agent “skills” (e.g., OpenAI Codex or Cursor agents). It combines static signatures, AST data‑flow analysis, and an optional LLM judge, with a CEL‑based decision layer, to detect prompt‑injection, data‑exfiltration, and malicious code patterns. It offers preset policies, CI/CD integration (SARIF, GitHub Actions, pre‑commit), and extensibility via custom rule packs and cloud‑LLM providers.

0 is an open‑source, AI‑driven security‑workflow platform. Install a tiny binary, configure an LLM provider, then run pre‑built or custom security templates (code review, dependency scan, smart‑contract audit, etc.) via a browser UI, CLI, or remote MCP server. Results are stored locally with evidence and suggested fixes, and the system integrates with common dev‑ops tools (GitHub, CI, Slack, etc.). It’s a research‑preview tool licensed MIT/Apache‑2.0.

N.E.K.O. is an open‑source AI companion that combines voice, text, and visual understanding with a five‑layer memory system and multiple avatar forms. It runs locally (Python 3.11) and can be deployed via one‑click binaries, Docker, or source build. Features include proactive chat, real‑time multimodal interaction, agent‑style tool execution, a plugin marketplace, and support for 14+ LLM providers. The project is Apache‑2.0 licensed and has active Discord/QQ/Steam communities.

Reasonix is an open‑source, locally‑run AI coding assistant that can read, edit, and execute code in your project. You configure any OpenAI‑compatible model (DeepSeek preset included) and interact via a desktop app, terminal, web UI, or VS Code extension. Features include permission levels, file‑level rewind, plugin‑driven tools, multi‑model composition, and a single‑binary distribution. Install via platform‑specific installers (2.x Studio) or npm (1.x CLI), then describe tasks in plain language and let the assistant modify your code under your supervision.

A curated collection of technical resources for learning GPU performance engineering and building high-efficiency AI inference systems.

A multi-modal world model framework that generates and reconstructs editable 3D assets (meshes and Gaussian Splattings) from text, images, or video for use in game engines.

Runner is a native macOS/Windows app that lets you combine multiple AI coding agents (Claude Code, Codex, Copilot CLI, etc.) into reusable crews. Each agent runs in its own real terminal pane, shares a mission feed, and persists via a background daemon. The UI supports split panes, notifications, theming, and a full CLI (`runner`) for script‑driven control.

This project provides a complete Chinese translation of Stanford's CS146S course on vibe coding and AI-assisted software engineering. It includes slides, assignments, and reading materials, making the latest practices in AI-native development accessible to Chinese-speaking learners.

Pyramid is a Python framework for ab initio molecular dynamics that intelligently combines accurate but slow reference calculations with fast machine-learned potentials, using a force-error method to decide when to invoke each. It supports adaptive MD, multiple time stepping, validation layers, checkpoint/resume, and plugin backends, with a focus on extensibility and safe workflows.

A plugin for the AstrBot framework that provides AI agents with long-term memory by storing and retrieving user preferences, relationships, and historical context using vector search and knowledge graphs.

Ray is a unified framework for scaling Python and AI applications from a single laptop to a distributed cluster, providing a core runtime and specialized libraries for ML compute.

Loop Engineering is a CLI framework that lets you design, run, and score autonomous LLM‑agent loops (e.g., daily triage, PR babysitter) around a code repository. It provides ready‑made patterns, a STATE.md persistence file, safety checklists, and a progressive L1‑L3 scoring system to move from report‑only to fully unattended automation.

A self-hosted AI workspace that transforms chatbots into digital teams by providing a governed runtime for humans, AI actors, and remote agents to collaborate in shared conversations.

Microsoft's free, hands-on curriculum that teaches beginners the Model Context Protocol (MCP) — a standard for connecting AI models to tools — with code examples in six programming languages, translations into 50+ languages, and a module path from fundamentals to production-ready builds.

A structured AI video production workflow that helps creators transform stories into multi-episode video series using Seedance 2.0 and AI agent automation.

An industrial-scale scriptwriting system for high-conversion short dramas, using structured emotional engineering and automated validation to ensure hit-worthy pacing and monetization.

Letta is an open‑source framework for building stateful AI agents with persistent memory. It provides a CLI, a self‑hosted server, channel integrations (Slack, Telegram, Discord), a TypeScript SDK, and optional cloud storage for memory, enabling agents that can learn and retain context over time.

edge‑tts is a Python package and CLI that calls Microsoft Edge’s online neural text‑to‑speech service. Install via `pip`/`pipx`, then generate MP3/audio files or play them instantly. It supports hundreds of voices, rate/volume/pitch tweaks, and shows a progress bar. The library is used in Home Assistant, Podcastfy, and other projects.