Trending AI projects

A Model Context Protocol (MCP) server that provides a universal memory layer, allowing users to carry their personal memories and context across different LLMs and AI clients.

An open-source website data extraction platform that converts public pages into cleaned markdown and hierarchical link trees for AI agents.

A solution accelerator for Databricks that ingests, indexes, and analyzes medical DICOM images, enabling AI-powered segmentation and secure, SQL-based research workflows.

An iOS and macOS Markdown renderer optimized for LLM streaming, providing smooth transitions, LaTeX support, and inline citation UI.

An interactive browser UI for AI brainstorming that replaces terminal typing with visual inputs and parallel exploration branches.

A template for building AI-driven workflow automation platforms, featuring a visual drag-and-drop builder that generates executable TypeScript code.

A Python library for automated feature engineering that uses Deep Feature Synthesis to automatically create feature matrices from multi-table datasets for machine learning.

An AI-powered pipeline that extracts data from resumes and GitHub profiles to rank candidates using explainable, role-specific scoring rubrics.

An AI coding assistant for Xcode that provides intelligent code completions, chat, and an agentic mode for Swift and Objective-C development.

Liger Kernel is a collection of high-performance Triton kernels that optimize LLM training by reducing memory usage by up to 80% and increasing throughput by 20% through efficient kernel fusion.

A 3D interactive visualization tool that displays the network topology and inference process of GPT-style Large Language Models.

An umbrella project providing a suite of safety tools and cybersecurity benchmarks to help developers build and deploy open generative AI models responsibly.

An open-source identity and access layer for AI agents that provides standardized authentication, permissions, and observability across thousands of external system integrations.

A simple LLM client for Emacs that allows users to interact with multiple AI models and backends directly within any buffer.

Flux Gym provides a Gradio web UI that lets you train FLUX diffusion LoRAs on 12‑20 GB GPUs. It wraps Kohya‑ss training scripts, offering full script options, automatic model download, optional sample‑image generation, and one‑click publishing to Hugging Face. Install via Pinokio, Docker, or manual venv setup.

A local, zero-config codebase intelligence engine that provides AI assistants with deep semantic understanding, dependency graphs, and symbol-level impact analysis for large repositories.

A Python package that integrates AI frameworks with geospatial data analysis, providing tools for satellite imagery processing, model training, and inference.

A population-scale infrastructure for evaluating AI systems and products by simulating diverse, persona-driven LLM agents across web, app, and chat environments.

A self-hosted terminal AI assistant and Python framework that provides a complete agent harness with a unique live run forking capability to test parallel execution paths.

A collection of AI-powered security tools for Solidity smart contracts, providing automated auditing, threat modeling, and fuzz testing suite generation.

An autonomous crypto trading system that uses a multi-LLM council for market analysis and deterministic Python risk gates to enforce strict capital management.

OpenCode2API is a Node.js proxy that turns a local OpenCode AI runtime into an OpenAI‑compatible API (including chat, streaming, and Anthropic endpoints). It adds reasoning control, tool‑calling, session continuation, health/metrics endpoints, and an optional web dashboard, and can be deployed with a single Docker compose command.

A spec-driven evaluation framework that turns natural language requirements into executable test suites for AI agents, featuring trace-grounded judgment and sandboxed testing.

Rebucca is a video surveillance and intelligent analysis platform that ingests streams via GB28181/RTSP/ONVIF, runs real-time object detection with D-FINE or YOLO small models, and optionally uses an OpenAI-compatible large model for re-verification. It provides polygon-based alerting with seven post-processing rules and atomic snapshot-backed alarms.

AgentCore CLI is a command-line tool and interactive terminal UI that simplifies creating, deploying, and invoking AI agents on Amazon Bedrock AgentCore. It handles AWS service complexities and offers both scriptable JSON output and guided interactive flows.

Nami is a unified workspace for running multiple AI agents simultaneously from a single local folder, allowing users to automate tasks using plain English commands.

A high-fidelity LLM inference system simulator used to study performance, plan capacity, and test scheduling optimizations without requiring continuous GPU access.

nurb is a locally‑run Python/macOS app that lets you describe a 3‑D part in plain language, has your existing LLM write real B‑Rep CAD code, checks the model against 13 print‑ability rules, shows live updates in a three.js viewer, and exports print‑ready 3MF (or STL/STEP/GLB) with slicer settings embedded.

A desktop application for producing long-form audiobooks, podcasts, and AI-generated videos by combining local text-to-speech engines with a structured visual storyboard workflow.

Yank Note is a highly extensible Markdown editor that integrates AI copilot features, code execution, and plugin support to create a powerful, local-first productivity environment.

Quotio is a management tool for AI coding agents that tracks provider usage quotas, manages API credentials, and configures local proxies from a native macOS app or a terminal CLI.

A cross-platform Arduino library that simplifies Field Oriented Control (FOC) for BLDC and stepper motors, making high-performance motor control accessible to hobbyists and researchers.

Codex Tools is a management utility for Codex users that provides multi-account switching, usage tracking, account pre-warming, and a local OpenAI-compatible API proxy for integrating Codex into other applications.

A one-stop creation suite for CS2 that automates demo analysis, highlight recording via OBS, and video editing with AI-powered commentary.

A Neovim plugin that integrates Anthropic's Claude Code AI assistant by reverse-engineering its WebSocket-based protocol, enabling AI-powered coding directly within the editor.

A multi-platform AI translator and text processor that provides translation, polishing, and summarization across 55 languages using LLM providers.

Humanity's Last Exam (HLE) is a multi-modal benchmark consisting of 2,500 expert-developed questions across various academic subjects to test the limits of AI knowledge.

Firecrawl CLI is a terminal tool that connects to the Firecrawl AI‑powered web‑scraping and search service. It lets you scrape pages (markdown, HTML, JSON, screenshots, etc.), run web searches with highlights, query specialised developer or government indexes, and install “skills” that teach popular AI coding assistants (Claude Code, Cursor, OpenClaw, etc.) how to use Firecrawl automatically. Authentication is interactive or via API key, and you can point the CLI at a self‑hosted Firecrawl instance. Install with `npm i -g firecrawl-cli` and start with `firecrawl <url>` or `firecrawl search "query"`.

A tool that creates persistent, isolated Linux workspaces using Docker or Podman to provide secure environments for software development and AI coding agents.

An AI residency runtime for Kelivo companions that enables proactive wake-ups and mobile notifications, giving AI characters a continuous sense of time and time-aware autonomy.

MiniCode is a small, terminal‑first AI coding assistant that implements a Claude‑Code‑style model‑tool‑model loop. It lets you issue natural‑language requests, runs built‑in tools (file edit, search, shell, web fetch), maintains in‑memory plans/goals, and shows a full‑screen TUI where you approve changes before they’re written. Designed for learning and extensibility, it runs locally via Anthropic/Claude or any model exposed through the Sidrune AI unified API.

A toolkit that adds Model Context Protocol (MCP) support to 1С:Enterprise, letting AI assistants query 1С data via custom tools. Includes a ready‑made 1С extension and an optional Python/OAuth2 proxy (Docker‑ready).

A comprehensive suite of Claude Code skills and agents for AI-powered penetration testing, bug bounty hunting, and AI threat testing.

An open-source SDK for deploying real-time interactive AI avatars on mobile and embedded devices with low latency and on-device execution.

A Python toolkit for RAG research that provides a modular framework, 23 SOTA algorithms, and 36 benchmark datasets to simplify the reproduction and development of retrieval-augmented generation systems.

A local-first scientific writing workspace that integrates LaTeX, Python, and Claude AI to help researchers write papers and perform data analysis offline.

ESP-SR is Espressif's official speech-recognition framework for their ESP32 microcontroller line. It packs wake-word detection ("Hi ESP", "Alexa", "你好小智" etc.), offline command recognition (up to 300 phrases in Chinese/English), audio front-end cleaning (echo cancellation, noise suppression, direction-of-arrival), voice-activity detection, and text-to-speech — all designed to run locally on small, low-power embedded chips.

A framework for generating expressive, long-form, multi-speaker conversational audio from text, capable of producing podcasts up to 90 minutes long.