Trending AI projects

cocoindex‑code is a real, open‑source tool that builds an AST‑based semantic index of a codebase and lets you search it with natural‑language queries. Install via pipx (full or slim variant), run `ccc init` and `ccc index`, then use `ccc search` or integrate the provided `ccc` skill/MCP server with Claude, Grok, Oh My Pi, Codex, etc. Docker images are also available for reproducible deployments.

A framework for building low-latency, multi-modal AI agents that can watch, listen, and understand video in real time using a combination of CV models and LLMs.

NVIDIA FLARE is an open-source Python SDK for federated learning and computing that allows multiple sites to collaborate on AI training and data analysis while keeping their raw data local and secure.

Dramaxis is an open‑source desktop app that uses a Rust‑based multi‑agent system and Tauri 2 to turn raw video into AI‑generated short‑film or commentary clips. It extracts scenes, writes a hook script, clones a voice‑over, aligns audio‑video on a 5‑track timeline, and exports a CapCut‑compatible draft for easy publishing across eight major short‑video platforms.

Alexandria is a locally‑run web app that converts a text file (txt/md/epub) into a complete audiobook. It uses an LLM to annotate the book with speaker tags and TTS instructions, then synthesises each line with the built‑in Qwen‑3 TTS engine. Users can pick from nine preset voices, clone a voice from a short sample, fine‑tune voices with LoRA, or generate new voices from textual descriptions. The UI lets you edit the script, batch‑render audio (GPU‑accelerated), and export as MP3, M4B, or per‑speaker WAV tracks for Audacity.

A local-first tool that boots disposable Linux microVMs for AI agents — fast, isolated, and reset every run.

MoveIt 2 is an open-source motion planning framework for ROS 2 used to develop robotic manipulation applications and benchmark planning algorithms.

nnsight is a Python library for tracing, reading, and editing the internal tensors of any PyTorch model (including Hugging Face Transformers, Diffusers, and vLLM). It lets you intervene in a model’s forward pass with simple Python syntax, supports gradient capture, generation‑step hooks, batch‑wise prompts, and remote execution via NDIF, making it useful for interpretability research and custom LLM tooling.

A C++ library and CLI tool that enables high-performance, Python-free inference for Stable Diffusion models using ONNXRuntime across multiple platforms.

Strands Agents Samples provides Python and TypeScript example projects that demonstrate how to build, deploy, and integrate AI agents using the Strands model‑driven SDK. It includes tutorials ranging from a simple hello‑world agent to advanced patterns like multi‑agent systems, RAG, cloud deployment, and edge/robotics integration.

A Chinese-language, community-maintained guide collecting ChatGPT and AI resources — from prompts and apps to model ecosystems, development guides, and frontier topics — with a Telegram community and open contribution model.

A PostgreSQL extension providing a high-performance, scalable vector search index (PRISM) that uses hierarchical clustering and quantization to outperform standard HNSW and IVFFlat methods.

jev-chat-jarvis-mac is a macOS-only read-only assistant that watches chat messages via screen OCR or system text interface, analyzes intent and risk with a local model, and suggests click-to-fill reply candidates in a floating panel. It does not inject, hook, or auto-send anything, and keeps all data local unless you opt into a cloud API.

OKF Agent Memory is a Go‑based, Git‑native toolkit that provides a fast, zero‑cost, token‑efficient persistent knowledge base for AI coding agents. It splits a tiny normative “push” layer (AGENTS.md) from a larger semantic “pull” layer (OKF v0.2 bundle in `knowledge/`), offers a BM25 search CLI, quality scorecards, vendor bundle handling, and an MCP server for direct agent integration.

Access to Anthropic's safety-first language model APIs in TypeScript

An automated pipeline that transforms a topic into a professional 4K video podcast by integrating research, script generation, TTS, and Remotion rendering.

Skales is a proprietary, local-first AI agent that runs on your desktop and mobile, performing real tasks like coding, designing, planning, and interacting with your files and apps — while keeping data on your machine and offering a free built-in trial model.

PyTorch is an open‑source Python library that offers GPU‑accelerated tensor operations and a dynamic, tape‑based autograd system for building and training deep neural networks. It integrates tightly with Python, supports extensions in C/C++ and other languages, and provides fast, low‑overhead execution on CPUs, NVIDIA GPUs, AMD ROCm, and Intel GPUs.

A curated, annotated list of 443+ verified resources for building and evaluating AI agents, with a runnable code playbook, deep reading notes, and a must-read starter set.

Things MCP Server is a Model Context Protocol server that connects AI assistants like ChatGPT and Claude to the Things 3 app on macOS, letting them list, create, update, and search tasks, projects, and areas directly from a chat.

AutoKernel is an autonomous GPU kernel optimizer that takes any PyTorch model, profiles it to find slow kernels, then uses an AI agent to iteratively rewrite and benchmark Triton or CUDA C++ kernels overnight. It verifies correctness and reports the total speedup, saving developers from manual kernel tuning.

FOREST is an end-to-end research agent framework that manages scientific projects as an editable graph, connecting hypotheses, experiments, and evidence to prevent research drift and ensure traceable results.

A resilient, tightly-coupled multi-sensor SLAM framework that maintains accurate localization for wheeled, legged, and aerial robots even during sensor degradation or calibration errors.

Cyrus is an AI agent orchestrator that monitors issues in Linear, GitHub, GitLab, or Slack and uses AI coding agents to automatically resolve them in isolated Git worktrees.

A Gymnasium‑compatible PyBullet simulator for single‑ and multi‑drone control, with examples for PID, downwash, and PPO reinforcement learning, plus optional Betaflight SITL integration.

A lightweight reinforcement learning framework for training motion controllers to imitate reference motions across multiple simulator backends.

An integrated AI platform for enterprise model routing, multimodal chat, and RAG, providing a unified interface for multiple AI model providers with built-in billing and identity management.

The repository provides a collection of 52 AI‑driven “skills” that turn any LLM into a full‑stack affiliate‑marketing assistant, covering research, content creation, landing‑page building, analytics and automation, with a closed‑loop flywheel and a tiny CLI for testing.

An open-source tool for data quality that uses Expectations to provide unit tests for data and automated documentation for validation results.

A modern, asynchronous web scraping and browser automation library for Python that simplifies data extraction, proxy management, and bot-evasion for reliable crawling.

A privacy-first, open-source Android app that consolidates multiple AI assistants into a single, customizable interface with built-in ad and tracker blocking.

A mobile companion for the Codex CLI that lets you monitor and steer AI coding sessions from your phone while keeping all work on your local computer.

ComfyUI‑Easy‑Use is a comprehensive set of custom nodes that streamline building Stable Diffusion (and other diffusion model) workflows in the ComfyUI visual editor. It adds one‑click loaders, prompt helpers, LoRA/ControlNet stacks, loop/conditional logic, image utilities, and UI tweaks, letting users create and run complex generation pipelines with far fewer nodes.

Codex Router is a client‑side tool that lets the Codex app use many LLM providers (Anthropic, Kimi, DeepSeek, Grok, Claude, Gemini, etc.) via a secure background service, Electron control center, and optional macOS widget. It manages credentials locally, offers experimental bridges to existing Claude/Cursor/Gemini agents, and provides a Homebrew tap for CLI‑only installs.

OpenTag is an open‑source, self‑hosted AI knowledge‑work assistant for Slack and Microsoft Teams. It combines a Python LangGraph agent (model‑driven, tool‑enabled) with a Node.js runtime built on CopilotKit’s Channels SDK, handling platform credentials via CopilotKit Intelligence. The repo includes quick‑start scripts, deployment configs for Railway or AWS, and UI components that render charts, tables, and approval buttons directly in chat.

A lightweight LiDAR-inertial odometry and mapping system that provides robust pose estimation and degeneracy detection for robots using ROS 2.

PaperRead is a desktop research workspace that guides you from paper discovery to deep reading. It helps you search, organize candidates, track reading status, generate grounded summaries, and read with AI assistance — all in a single Traditional Chinese-first interface.

CLI2API is a Docker‑based gateway that turns personal login sessions for Qoder, WorkBuddy, Trae, and experimental Devin/Command Code into a local OpenAI‑compatible API, with a web console for account and key management.

A proxy tool that enables local MCP clients to connect to remote, authenticated MCP servers by handling OAuth flows and protocol translation.

Video to Data (V2D) is a modular, container‑based pipeline that converts ordinary human‑demo videos into 3‑D reconstruction assets and physics‑grounded robot RL policies, using LangGraph‑driven video ingestion, a suite of vision modules (depth, masks, meshes, SMPL), and NVIDIA Isaac Lab for training.

RoboLab is a high-fidelity simulation benchmark built on NVIDIA Isaac Lab that provides over 100 manipulation tasks to evaluate and compare generalist robot policies.

A plugin for DeepSeek Harness that integrates AnySearch to provide real-time web search, URL content cleaning, and specialized vertical search capabilities for AI agents.

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”.

An AI software factory that automates the development loop from issue triage to draft pull request using a pipeline of specialized AI agents.

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.