Trending AI projects

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).

An MCP server that connects Claude and ChatGPT to the Intervals.icu API, enabling AI assistants to retrieve and manage athletic training, wellness, and event data.

A self-hosted AI image and video generation workbench that allows users to bring their own models and extend functionality via a plugin system.

A Python library for removing image backgrounds, offering a choice between free local open-weights inference and a high-quality cloud API.

A deployment recipe for serving the Qwen3.8-Flash-Next vision-language model on a single DGX Spark using vLLM, with memory optimizations, speculative decoding, and extensive benchmark data.

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

ProjectAtlas is a Rust-native CLI and MCP server that creates a local, intelligent map of your codebase to help AI coding agents navigate large repositories more efficiently and reduce token costs.

A local video studio for your coding agent: describe a video, your agent directs, your machine renders — no cloud, no API keys.

An open-source desktop app that runs AI coding-agent CLIs in parallel, each isolated in its own git worktree with optional sandboxing.

A versatile 3D mapping framework that uses factor graphs and GPU acceleration to provide accurate, sensor-agnostic range-based mapping and localization.

An ACP adapter that integrates the pi coding agent into ACP-compliant editors like Zed, enabling editor-integrated AI coding assistance.

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 high-performance local tool for searching and deduplicating massive image and video collections using perceptual hashing algorithms.

WyckoffAgent is an open‑source, AI‑driven trading assistant that lets you converse with a “Wyckoff master” to analyse Chinese, Hong‑Kong and US stocks. It pulls real‑time data from TickFlow, identifies Wyckoff structures, generates LLM‑based research reports, and presents results via a React web UI, a terminal dashboard, or an Electron desktop app. All user data (portfolio, signals, back‑tests) lives in Supabase, and write actions go through an approval queue. The project is AGPL‑3.0, installable via Homebrew or pip, and includes detailed cost and architecture docs.

A privacy-focused Android app that runs LLMs locally on your phone, serving as both an on-device chatbot and a local network server for AI tasks.

A library of 200+ specialized AI workflows that integrate with coding agents like Claude Code and Cursor to automate business growth tasks such as lead generation, SEO, and competitive research.

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

A scalable framework for extracting and structuring text, tables, and charts from complex documents to power retrieval-augmented generation (RAG) pipelines.

A desktop application for AI-powered face swapping and enhancement across images, videos, and live webcam feeds, featuring professional editing tools and GPU acceleration.

Comark is a TypeScript‑based Markdown parser that produces a compact, serialisable AST and offers framework‑specific renderers (React, Vue, Svelte, Angular, HTML, ANSI). It supports CommonMark/GFM, custom component syntax, and streaming‑ready auto‑closing, making it useful for live or LLM‑generated content.

An official Model Context Protocol (MCP) server that enables LLMs to use Qdrant as a semantic memory layer for storing and retrieving information.

An open-source secure virtual desktop designed for AI agents to perform 'Computer Use' tasks via programmatic GUI control and screen streaming.

A community-driven Chinese learning resource that provides translations, knowledge summaries, and code explanations for the DeepLearning.AI course on building AI agent skills with Anthropic's Claude.

Cohub is a collaborative workspace where humans and AI agents co-create apps, games, and automations across multiple platforms.

An end-to-end audio foundation model designed for low-latency, real-time speech-to-speech conversations, ASR, and TTS.

A zero-code desktop application for DeepSeek Harness that provides a visual interface for managing AI agents, plugins, and local model inference.

BiBi Keyboard is an Android voice input method that uses AI speech recognition from multiple cloud and on-device engines to turn speech into text, then optionally polishes it with LLMs. It works as a standalone keyboard, as a floating ball over any app, and integrates with other input methods via an IME bridge.

Agents‑Flex is a modular, Java‑first framework that bundles chat, embeddings, tool calling, RAG, vector stores, and production‑grade features (routing, observability, persistence) into interchangeable Maven modules, letting JVM developers build LLM‑driven agents, chatbots, and AI‑enhanced services without leaving the Java ecosystem.

Tensorlake is a cloud platform that offers fast, scalable MicroVM sandboxes for running AI agents safely. It provides a Python SDK and CLI to create, manage, snapshot, and pool sandboxes, a versioned object‑store filesystem, and a serverless orchestration layer where functions (decorated with `@function`) run in isolated sandboxes and can be invoked via HTTP.

grepai is a privacy-first, local CLI tool that uses vector embeddings to enable semantic code search, helping developers find code by intent and reducing token usage for AI coding agents.

A Python app that gives the Reachy Mini robot real‑time voice conversation, vision, and motion by connecting to Hugging Face realtime speech services and an LLM. It supports local VAD, persistent memory, extensible tool plugins (dance, head tracking, web search, weather, etc.), and a web UI for managing personalities and settings.

A collection of reusable skills, extensions, and prompt commands for the Pi Coding Agent to enhance its capabilities and workflow automation.

A tool that turns software repositories into agent-ready workspaces by providing a structured protocol and navigation tools to help AI coding agents follow authoritative project context.

A speaker diarization pipeline that combines OpenAI Whisper for transcription with NVIDIA NeMo for speaker identification to determine who spoke which words in an audio file.

A high-performance data platform for robotics and Physical AI that transforms monolithic sensor logs into structured, queryable archives for model training.

A middleware for LLM inference engines that enables rapid, in-place model weight updates across large GPU clusters, essential for reinforcement learning.

An open-source, clean-room implementation of the Claude Code CLI that provides an agentic terminal interface for coding tasks, supporting custom tools, MCP integration, and multiple AI providers.

A universal infrastructure for autonomously evolving AI agents by mutating their workspace files (prompts, skills, and memory) to improve performance across any domain.

A collection of domain-specific skills for Claude Code that provide deep expertise in copywriting, frontend design, SEO, and video production via slash commands.

A curated collection of 115 beginner-friendly data science projects with real datasets, clear explanations, and working code, organized by category and difficulty, with a learning path and easy setup.

Awesome Data Agents is a curated, survey-backed reading list that classifies LLM-based data agents into six autonomy levels (L0–L5), organizes papers by task type (data management, preparation, analysis), and includes benchmarks, tutorials, and a KDD Cup 2026 competition.

Image To Slice is a Figma plugin (with a web UI) that uses AI to split a UI screenshot into editable layers and image assets, then exports the result as a Figma file or HTML/CSS bundle. It supports automatic AI slicing, manual JSON mode, background inpainting, asset classification, and configurable OpenAI‑compatible back‑ends.

A curated list of open-source TTS and voice generation models, sorted by release date, with a comparison table and detailed entries covering features like voice cloning, language support, streaming, and licensing.

Fonoster is an open‑source platform for building AI‑driven voice agents that run on real phone lines. It provides multitenant PBX features, a CLI, TypeScript/Python SDKs, and built‑in integrations with speech‑to‑text, text‑to‑speech, and LLM services (e.g., OpenAI). You can create bots declaratively with a YAML *Autopilot* file or programmatically via a WebSocket session. The stack is self‑hostable (Docker) and aims to be an open alternative to Twilio for voice‑AI applications.

A multi-agent collaboration framework for intelligent penetration testing and CTF scenarios that automates vulnerability discovery and attack chain execution.

A community-run, free referral list for embodied AI (robotics) jobs, aggregating long-term and rolling openings from companies, labs, and universities, plus learning resources and career support.

An MCP server for jailbroken iPhones that enables AI agents to control the device via touch gestures, app management, and system-level access.

A comprehensive, 14-week open-source curriculum covering the entire spectrum of Natural Language Processing, from foundational word embeddings to modern LLM systems and AI agents.