Trending AI projects

A benchmark for evaluating how AI agents leverage and compose modular skills—instructions, scripts, and resources—to perform specialized workflows.

A plugin that provides AI coding agents with curated Azure expertise and over 200 execution tools via MCP to perform real cloud infrastructure tasks.

A self-hosted, open-source alternative to LangSmith Deployments that allows you to run LangGraph agents on your own infrastructure using the same SDK and APIs.

An open-source, self-hosted platform for Generative Engine Optimization (GEO) that helps brands increase their visibility and citations in AI engine answers through a structured audit-to-execution workflow.

Burrow is a free, open‑source macOS (stable) and Windows (preview) utility that bundles a Rust engine to provide junk‑file cleanup, dev‑artifact purging, installer sweeping, app uninstall, disk‑usage treemap, live system monitoring, and long‑term metric history. It also runs an MCP JSON‑RPC/HTTP server so AI agents (Claude Code, Cursor, etc.) can query the machine’s state and, with user consent, invoke these maintenance actions.

Code World Model is a framework that positions a coding agent as a world brain to better understand and manipulate its operating environment.

A self‑hosted memory backend for LLM agents that provides a REST API, CLI, OAuth, and a web dashboard. It stores facts, decisions, and causal knowledge graphs locally (SQLite + ONNX embeddings) or in hybrid/cloud mode, offering fast (≈5 ms) semantic search, tag‑scoped retrieval, and optional LLM‑generated summaries. Works with LangGraph, CrewAI, AutoGen, Claude Desktop, ChatGPT, and many other tools.

A cross-platform desktop application for AI-assisted video masking, segmentation, and object removal using models like SAM2 and MatAnyone.

LongHorizon‑Harness is an open‑source Python framework that adds a robust planning‑act‑verify‑checkpoint loop around existing LLM agents (Claude Code, Codex, OpenCode, DeepSeek Harness). It enables those agents to run for hours across desktop applications and the terminal, automatically handling failures, context refreshes, and verification. The project offers a one‑command install, a web dashboard, multi‑backend support, and shows strong benchmark gains (e.g., 80.7 % pass rate on WeaveBench vs 51.8 % baseline).

MCP Registry is an API‑driven “app store” for Model Context Protocol servers, letting clients discover validated model‑hosting endpoints. It offers a stable v0.1 API, Docker‑based dev setup, a publishing CLI with GitHub/DNS auth, and community‑driven governance.

Temps is an open‑source, self‑hosted platform that bundles AI‑driven deployment, monitoring, analytics, error tracking, email, and secure sandbox execution into a single dashboard, letting you replace many SaaS tools with one binary.

The official Model Context Protocol (MCP) server for Atlassian, providing AI tools with secure, real-time access to Jira, Confluence, and other Atlassian Cloud products.

A governance and engineering system that transforms rough workflows and prompts into reusable, cross-platform AI agent skill packages with built-in evaluation and release gates.

A node-based visual programming framework for 3D reconstruction and computer vision, enabling users to build complex data processing pipelines using AI and photogrammetry.

**Key capabilities** - **AI‑driven**: Uses ChatGPT, Claude, or any OpenAI‑compatible API to write cover letters, answer test questions, and chat responses. - **Resume management**: Auto‑refresh resumes, and filter out unwanted vacancies (e.g., “courier” or taxi jobs) using regex or AI. - **Captcha solving**: Recognizes and auto‑fills captcha. - **Email outreach**: Can also send extra emails to employers. - **Chat auto‑responder**: Replies to employer chats, including handling multiple‑choice buttons. - **Multi‑account**: Supports separate profiles for different hh.ru accounts. - **Local & private**: All data stays on your device; it doesn’t use a headless browser, so it’s lightweight and works on low‑cost servers. - **Fully configurable**: All prompts and filters are editable in a config file.

Delta Lake is an open-source storage framework that brings data-warehouse-like reliability (ACID transactions, serializable concurrency) to data lakes, working with engines like Spark, Flink, Trino, and Hive. It uses a transaction log protocol, guarantees backward compatibility for tables, and requires storage systems to provide atomic visibility, mutual exclusion, and consistent listing. Built with SBT (Java 17+), licensed under Apache 2.0, with community support via Slack, LinkedIn, YouTube, and a mailing list.

A curated, comprehensive directory of publicly available medical datasets and research resources designed to support healthcare AI development and clinical research.

Lorca is a self-hosted, end-to-end encrypted bot orchestration platform that runs bots on your own machines and lets them collaborate in group chats. It includes desktop apps, a CLI, and mobile apps, supporting multiple AI providers and offering a private alternative to cloud bot services.

A curated directory of high-quality, remote Model Context Protocol (MCP) servers that allow AI applications to securely connect to external tools and services over the internet.

An AI-powered tool that uses local ASR and LLMs to automatically identify and export highlight clips from long-form videos.

A pure C# inference library for PP-OCRv6 that provides high-performance OCR without requiring native dependencies like ONNX Runtime or OpenCV.

A pipeline that converts locked-camera videos into clean FK animations for Mixamo characters, removing the need for mocap suits or manual keyframing.

An open-source toolbox for markerless human motion capture and novel view synthesis from RGB videos, supporting various input sources from multi-view setups to internet videos.

ai-usagebar is a system monitoring tool that displays real‑time quota usage for a wide range of AI coding services (Claude, Codex, GitHub Copilot, OpenRouter, DeepSeek, and many more) as a desktop widget, terminal UI, or JSON feed. It reuses existing credentials from the official CLIs, automatically refreshes tokens, and provides threshold alerts and reset timers.

A set of output-style guidelines and plugins for Claude and other LLMs to prevent broken machine-Korean and ensure clear, natural, and unambiguous Korean communication.

A multimodal toolbox for evaluating embeddings and retrieval systems, providing a standardized benchmark and leaderboard for comparing model performance.

A multi-platform package manager and inference interface for Stable Diffusion that provides one-click installation and shared model management across multiple Web UI packages.

Kiln is an open‑source, local‑first workbench (desktop app + Python library) that lets teams build, evaluate, optimize, and ship LLM‑based products. It covers eval creation, prompt auto‑optimization, RAG pipelines, multi‑agent hierarchies, synthetic data generation, and zero‑code fine‑tuning across 190+ models, with Git‑based collaboration and offline support.

Open Multi‑Agent (OMA) is a self‑hosted TypeScript runtime for building, coordinating, and auditing LLM‑powered agent teams. It offers deterministic planning, human approval gates, a verifiable run journal, strict egress policies, and an offline Run Viewer, all without telemetry or a hosted backend.

A hybrid edge-cloud AI engine for mobile devices and wearables that optimizes inference for text, speech, and vision models using custom quantization and hardware-specific kernels.

A vision-language foundation model for autonomous driving that integrates 3D perception, visual question answering, and motion planning into a unified framework.

A specialized vLLM fork optimized for NVIDIA Turing (SM75) GPUs, enabling high-performance inference for 27B-35B parameter models on hardware like the RTX 2080 Ti.

A utility package for the Apple Foundation Models framework that provides chat completions clients, context window management, and dynamic skill activation for LLMs.

The ElevenLabs Python SDK is an official library that enables developers to integrate high-quality text-to-speech, voice cloning, and real-time conversational AI agents into their applications.

Olares is an open‑source personal‑cloud operating system that runs on your own Linux machine (or cluster). Built on Kubernetes, it offers a web UI and a suite of system apps (Files, Vault, Market, Dashboard) plus AI‑specific agents (Lares, OpenClaw). With one‑click model installation, GPU pooling, private networking, and CLI “Agent Skills,” it lets individuals or small teams host LLMs, generative‑AI tools, home‑automation, and collaborative workspaces while keeping data and compute local.

A collection of agent-ready skills for the App Store Connect CLI that enables AI assistants to automate iOS/macOS release, metadata, and distribution workflows.

A repository of custom character models for the BongoCat desktop overlay application, allowing users to replace the default animation with various community-created avatars.

An open-source, local-first visual prompt archive and agent-ready toolkit for retrieving traceable image-prompt references and defining art direction.

Birdview is a skill for AI coding agents that visualizes a project's architecture, constraints, and planned changes in a standalone HTML page. Developers confirm the AI's plan before any code is edited, helping catch scope mistakes early. It offers architecture reviews, constraint audits, and impact tracing, with bilingual UI and optional auto‑mode.

A self-hosted, private knowledge base and task management platform that features AI RAG capabilities, MCP support for AI agents, and multi-device synchronization.

Valen is a multimodal decision model that accepts text, images, or video and returns probabilities for user-defined choices, giving software a structured decision interface. It comes in three sizes, offers a free API, and includes training and evaluation tooling for building custom decision-making systems.

Iris is a pure C inference pipeline for generating images from text prompts using open-weight diffusion transformer models like FLUX.2, FLUX.3, and Z-Image-Turbo. It runs with zero external dependencies, supports GPU acceleration via Metal, CUDA, and ROCm, and can operate in low-memory environments using memory-mapped weights.

An autonomous orchestrator that keeps coding agents running in a loop, making incremental git-committed changes toward a goal while the user is away.

Anthropic’s *k12-teacher-skills* repo provides four Claude‑agent plugins for lesson‑plan creation, differentiation, prep, and formative checks, all built to use the Learning Commons Knowledge Graph for standards alignment. The skills are pre‑installed for Claude for Teachers users and can be added manually elsewhere; the repo also includes an evaluation framework for testing and adapting the skills.

Paper2Patent is an open‑source AI‑assisted pipeline that converts a research paper into a full Chinese invention‑patent draft (five sections, claims, drawings, and compliance checks). It provides prompt templates, a reusable “Skill” for Codex/Claude/Cursor/Windsurf, and Python scripts for auto‑checking, drawing generation, and DOCX/PDF export.

aimock is a zero‑dependency Node library that runs a local mock server for virtually every LLM, image/video/audio, vector‑store, and AI‑agent protocol. It lets you record real API calls as fixtures and replay them deterministically, inject chaos or model misbehaviour, and test your AI application without network calls or billing.

MLC LLM is a universal deployment engine and ML compiler that enables high-performance native execution of large language models across diverse hardware and platforms.

A collection of deep learning architectures and model implementations in PyTorch and TensorFlow, providing runnable Jupyter Notebooks for a wide variety of neural network types.