Trending AI projects

Airbyte is an open-source data movement platform that syncs data from hundreds of sources to warehouses or AI agents, providing an SDK to turn these connectors into LLM-ready tools.

HoloMotion is an end-to-end framework for humanoid robot control that enables real-time motion tracking and command following by converting diverse human motion data into actionable robot policies.

An MIT-licensed computer vision library that provides a unified API for over twenty vision tasks, including detection, segmentation, and pose estimation, with integrated training and export tools.

An MCP server and CLI tool that enables AI assistants to programmatically control Siemens TIA Portal for project generation, hardware configuration, and PLC/HMI development.

A curated directory of over 150 terminal-based AI coding agents that can autonomously read, edit, and execute code in your local development environment.

A video editing plugin for Claude that automates the creation of social media reels, motion graphics, and thumbnails by handling tasks like silence removal, captioning, and visual styling.

Paper2Poster is a multimodal automation system that converts scientific papers (PDF) into editable presentation posters (PPTX) using a multi-agent pipeline, and provides an evaluation benchmark (PaperQuiz, VLM-as-Judge, statistical metrics) to assess poster quality.

LIBERO-MAX is a robotics benchmark that measures how effectively robot policies adapt to unexpected environmental changes occurring mid-task by comparing performance across thousands of paired stable and dynamic scenarios.

A vendor-neutral standard for packaging reusable AI agent skills and MCP servers into portable, distributable plugins.

Terminal-Bench is a continuous benchmark for measuring the capabilities of frontier AI agents using a diverse and evolving set of difficult tasks.

A production-grade AI filmmaking tool that automates the entire pipeline from script parsing and character consistency to batch video generation.

A modern web UI for the oh-my-pi coding agent that provides a browser-based workspace for chatting, project management, and file previews.

An agentic platform for building and deploying full-stack applications on Cloudflare, featuring an AI coding agent that handles planning, file editing, and live previews.

Files and templates extracted from a 72-hour live-streamed build where three xAI engineers launched a product using coding agents — including agent rules, 40 documented failures, 69 role definitions, 9 role playbooks, and a PR template that forces proof-before-merge.

An AI-powered social media diagnostic tool that analyzes account performance, deconstructs viral content, and generates data-driven sales scripts and content strategies for creators.

This is a comprehensive, free guidebook for the Hermes Agent framework, detailing how to use its self-improving learning loops, multi-layer memory, and multi-agent orchestration features.

CLI Agent Orchestrator (CAO) is a Python tool that lets you run several AI‑coding command‑line interfaces (like Claude Code, Copilot CLI, etc.) as coordinated agents. It starts a local server, launches each provider CLI in its own tmux pane, and offers a web UI, API, and plugin system for building parallel or sequential code‑generation pipelines.

Leon is an open-source personal AI assistant that uses tools, context, and agentic workflows to perform tasks locally on your machine, prioritizing privacy and grounded, actionable behavior.

An Android application that functions as an MCP server, allowing AI models to remotely control device UI, manage files, and execute system actions directly from the phone.

OpenSquilla is a token‑efficient, locally‑run AI agent that routes each turn to the cheapest LLM, offering a unified CLI, desktop GUI, and chat‑channel integrations with built‑in memory, web‑search, and embeddings.

A local-first personal AI assistant with a transparent, lightweight codebase that implements core agent pillars like memory, loops, and evaluation.

mcptoon is a zero‑dependency Python CLI that dramatically reduces the token cost of using Model Context Protocol (MCP) tools and skills. It keeps only a compact name index in the LLM’s context (‑99 % tokens) and fetches full schemas on demand, works with 103+ AI agents, and provides a universal tool/skill registry, offline BM25 search, and a lightweight MCP server endpoint.

OpenWorkBuddy is a local-first AI workspace that acts as an autonomous agent to plan, execute, and generate editable office documents like PPTs and reports based on your instructions.

A context management plugin for OpenCode that reduces token usage by automatically summarizing stale conversation history and pruning redundant tool calls.

An agent-first linter for Tailwind design systems that provides AI coding agents with actionable feedback to ensure UI code adheres to design rules.

DeepSeek Harness Desktop is a cross‑platform (Windows, macOS, Linux) open‑source desktop client that bundles the DeepSeek AI‑coding runtime with a full IDE‑like UI. It provides LLM chat, code editing, Git integration, extensible Skills/plugins, agent‑driven task automation, remote‑SSH development, and a privacy‑first design, all packaged under a BSD‑3‑Clause license.

A collection of 120 installable AI marketing skills that function as a portable, automated marketing staff for AI agents, covering everything from SEO and social media to paid ads and product launches.

MCPHub is a self-hosted gateway and control plane that unifies, secures, and monitors multiple Model Context Protocol (MCP) servers for AI applications.

A collection of Model Context Protocol (MCP) servers that enable AI agents and coding assistants to securely access AWS documentation and manage cloud infrastructure.

An open-source automated video clipping tool that uses ASR and speaker recognition to extract video segments based on text or speaker identity.

Laminar is an open-source observability platform for AI agents that provides automated tracing, evaluation tools, and real-time monitoring to help developers debug and optimize agent performance.

KataGo is a superhuman open-source Go bot trained via self-play that provides advanced game analysis, score estimation, and support for multiple hardware backends.

RuVector is a Rust-native vector database and persistent memory substrate for AI agents. It combines local semantic embeddings, vector retrieval, graph relationships, and explicit feedback learning to give agents durable, cross-session memory and fast local decisions, with SDKs for Node.js, Python, Rust, and browser WebAssembly.

An open-source git extension that provides line-level attribution for AI-generated code, linking every line to the agent, model, and prompt that created it.

Agents-A1 is a 35B Mixture-of-Experts agentic model that achieves trillion-parameter-level performance by scaling agent trajectories and distilling specialized domain expertise.

Apify Agent Skills is a set of plug‑in modules that let LLM agents call the Apify platform for web‑scraping, automation, and custom serverless “Actors”. It provides a universal scraper covering 130+ popular sites, tools to create or wrap code as Actors, and guidance for building Apify integrations (Zapier‑style, LangChain wrappers, etc.). Install via the Claude Code plugin system (or similar) after setting up an Apify account and CLI. Use cases include lead generation, competitive intel, market research, brand monitoring, and influencer vetting. Pricing follows each Actor’s pay‑per‑result model; the project is Apache‑2.0 licensed.

A tool for creating LLM fine-tuning datasets by converting unstructured documents into high-quality structured QA pairs and evaluation sets.

LeanType is an open‑source Android keyboard built on HeliBoard that adds AI‑powered proofreading, translation, voice‑to‑text (Whisper), handwriting/OCR, offline GGUF LLM support, math evaluation, and extensive UI customisation, while keeping permissions minimal. Two flavors let you choose cloud‑AI or fully offline operation.

GLiNER2 is a Python library for unified, schema‑driven information extraction and text classification. It offers two model architectures (span‑grid and boundary start/end), runs locally on CPU or GPU, supports multilingual models, long‑document chunking, safety/PII checkpoints, and provides a simple API (`AutoExtractor.from_pretrained`) to extract entities, relations, records, and classifications in one pass.

WeMM-Embedding is a family of multimodal models that convert text, images, videos, and visual documents into unified numerical representations for cross-modal search and analysis.

backpass is a local-first developer tool that uses gradient descent on your agent sessions to improve AGENTS.md, CLAUDE.md, and skills by proposing evidence-backed edits, which you accept or reject.

This project provides a ready-to-run recipe for serving the GLM-5.3-Flash language model across two NVIDIA DGX Sparks using TensorFold, delivering an OpenAI-compatible API with a 1M-token context, image/video input, and high throughput at low latency.

MATLAB MCP Server is a Go‑based bridge that lets AI assistants (Claude, Copilot, Codex, etc.) start MATLAB, run scripts, perform static analysis, and run unit tests via the Model Context Protocol. It supports configurable launch options, custom tool extensions, and provides coding‑guideline resources. Install MATLAB R2021a+, download the binary, and integrate it with your AI tool using the provided CLI snippets.

An AI-powered image translator that detects, removes, and replaces text in comics and images, supporting multiple languages and providing automatic typesetting.

A multi-account API gateway that aggregates Grok Build, Web, and Console services into a single, standard OpenAI/Anthropic-compatible API for easier integration and management.

NVIDIA Warp is a Python library that JIT‑compiles annotated functions into fast CUDA/CPU kernels for physics simulation and geometry processing. Its kernels are differentiable, so they can be used inside PyTorch, JAX, etc., enabling end‑to‑end learning on simulations. Install via `pip install warp-lang`, write kernels with `@wp.kernel`, launch them with `wp.launch`, and convert results to NumPy or tensors. The repo ships many examples (particles, fluids, FEM, ray‑marching) and integrates with deep‑learning frameworks.

A project management framework and continuity engine for fiction writers that uses AI agents to draft, track, and validate narrative consistency in long-form stories.

A Claude Code skill that guides technical founders through the process of interviewing, scoping, launching, and iterating on agents built with Claude Managed Agents (CMA).