Trending AI projects

An open-source library for intelligent LLM routing that dynamically selects the most cost-effective and performant model for each query using over 16 routing strategies.

An open-source, collaborative workspace for building and deploying autonomous AI agents that can be accessed via chat platforms like Slack and Telegram.

An open-source AgentOS framework for building AI agents and orchestrating their cooperation through a hub-and-channel network system.

atopile is a declarative language, compiler, and VS Code extension for designing electronic circuits as code. It resolves constraints, picks parts, validates designs, and can generate KiCad PCB files, enabling reusable, parametric hardware development.

A plugin for the DeepSeek Harness web interface that enables workspace path references via an @-mention system, allowing users to easily point AI agents to specific files and directories.

A ComfyUI plugin that decomposes single anime illustrations into layered 2.5D models with depth ordering, specifically designed for Live2D workflows.

An open-source Agent Operating System built in Rust that runs autonomous agents on schedules to perform complex background tasks without constant prompting.

An AI-powered Rust development assistant that uses a meta-cognition framework to provide architecturally sound solutions instead of surface-level syntax fixes.

QGroundControl is an open-source ground control station for MAVLink drones, offering mission planning, live flight telemetry, and vehicle setup across Windows, macOS, Linux, Android, and iOS.

A React component library that draws animated 3‑D‑style robot heads on a canvas, changing facial expressions and motion to reflect an AI agent’s state.

A methodology and technical framework for building business management systems using an ontology-driven approach, ensuring strict alignment between requirements, models, and code.

ChatArchiveGuard is a Python‑only CLI that locally scans chat export files (text, JSON/JSONL, SQLite) for secret/PII patterns, format errors, and SQLite integrity, reporting aggregate counts and coverage flags without modifying or uploading data.

An automation tool that injects DLSS 5 neural rendering and updated DLSS runtimes into games that didn't ship with them, supporting a wide range of APIs and RTX hardware.

BoardUI is a React design system for AI-native applications that provides both standard dashboard components and specialized agent-specific UI elements, installable as source code for full customization.

An AI-native motion comic and video creation platform that transforms scripts into finished videos through an integrated pipeline of script analysis, asset generation, and composition.

An open-source durable execution platform for microservices and AI agents that turns complex workflow graphs into persisted, inspectable, and recoverable executions.

Ongrid is an open‑source AI ops platform that connects to Slack/Telegram, uses LLM‑powered coordinator and specialist agents to perform automated root‑cause analysis, observability queries, and controlled remediation across servers, Kubernetes clusters, and network devices. It ships with a one‑command installer, built‑in Prometheus/Loki/Tempo/Grafana stack, and supports any major LLM API.

ODM is a free command-line tool that converts drone photos into 3D models, point clouds, orthophotos, and elevation maps. It runs on Windows/Mac/Linux via Docker or native install, supports GPU acceleration and video input, and can be extended through its API or source code.

Contrastive Language Models (CLM) is a genuine AI project offering a fast, contrastively trained decision‑making model (CLM‑8B) that scores actions against textual states. It provides a pip‑installable library, a FastAPI server with a web playground, and a typed‑question API (binary, choice, score). The model achieves state‑of‑the‑art verification performance on agentic benchmarks while being up to 9× faster than comparable agents. It includes scripts for fine‑tuning the lightweight projection heads on custom data and is released under Apache 2.0.

A native Android client for the Hermes Agent that enables mobile access to chat sessions, memory, and task automation via a secure local or private network connection.

dsh-handbook is a community-driven manual for DeepSeek Harness (dsh), an open-source agent runtime. It provides a beginner-friendly path from installation to plugin development and performance tuning, with 15 chapters, tested commands, real case studies, and ecosystem insights. Available online and as a PDF, it targets developers, evaluators, and anyone wanting to build or customize AI agents on the dsh framework.

A collection of optimized Docker recipes and benchmarks for running LLMs locally on NVIDIA RTX 3090 and similar consumer GPUs, providing an OpenAI-compatible API for easy integration.

NobodyWho is a cross-platform inference engine that enables developers to run LLMs, speech-to-text, and vision models locally on mobile, desktop, and game engines.

Aegis is an open‑source method pack that adds disciplined, evidence‑based workflows to AI coding agents (Codex, Claude Code, OpenCode, DeepSeek, etc.). It improves safety (benchmark shows contract pass rate ↑ 31 pp, unsafe outcomes ↓ to 0), provides proof before a task is marked done, and supports multiple hosts via plugin installation. Installation is a single prompt to the agent followed by a verification script; optional activation and TDD modes can be toggled. The project is MIT‑licensed and includes a benchmark, extensive docs, and a Windows desktop client (Autoloom) that showcases the methods.

CARLA is an open‑source, Unreal‑Engine‑based autonomous‑driving simulator that provides realistic urban environments, customizable sensor suites, and a Python API for training, testing, and benchmarking self‑driving systems.

A Chinese-language, MIT-licensed course that teaches AI engineering by building each algorithm from scratch, with 542 lessons in 20 phases, reusable outputs, and AI-tutor support.

Leviathan is a Rust‑based CLI that indexes CSV/JSON/SQLite data into a single SQLite FTS5 file, enabling fast, token‑budgeted natural‑language search for AI agents. It supports group‑scoped queries, incremental upserts, optional key‑value memory, and can be wrapped as a skill for Claude, Gemini, VS Code/Copilot, etc. Benchmarks show ~436‑token answers for 1 M records with 33 ms latency, far smaller than raw grep approaches.

An open-source, low-cost desktop quadruped robot that integrates LLM-powered dialogue, gesture recognition, and 3D reconstruction for interactive AI companionship.

A curated collection of pre-trained, state-of-the-art machine learning models in the ONNX format, enabling cross-framework compatibility and deployment.

AgentField is an open-source control plane that transforms AI agent code into production-ready microservices, handling orchestration, scaling, and governance automatically.

An open-source world simulator that generates high-fidelity, interactive video environments with real-time interactivity and long-term temporal consistency.

An automated research workflow that searches, recommends, and analyzes academic papers from arXiv and Semantic Scholar, integrating the results directly into Obsidian notes.

A native macOS menu bar application that provides real-time monitoring of Claude AI usage limits, session windows, and API costs across multiple profiles.

A curated collection of high-fidelity prompts and techniques for Seedance 2.0, helping users create consistent, cinematic, and professional AI-generated videos.

A community-curated directory of Agent Skills — simple text files that teach AI assistants how to do specific tasks on demand. It organizes official skills from major AI companies (Anthropic, OpenAI, Google, etc.) and community-contributed skills, with tools for finding and managing them. Skills load in three stages (browse, load, use) and work across many AI agents like Claude Code, Codex, and GitHub Copilot.

A curated list of 132 example projects, tutorials, and recipes for building LLM-powered applications — covering text agents, voice assistants, RAG systems, MCP integrations, memory-enhanced agents, and fine-tuning — organized by category with links to each project's code.

A terminal-based code review interface for the herdr AI coding agent that lets you inspect diffs, comment on code, and send feedback to the agent without leaving your terminal.

A toolkit that turns Unity games and simulations into environments for training intelligent agents using reinforcement and imitation learning.

Second Brain is a Cloudflare‑hosted personal + team memory system that stores notes, decisions, and project facts and makes them searchable by meaning. It integrates with Claude, ChatGPT, Cursor, Obsidian, Notion, calendars, etc., and provides a secure, self‑hosted backend (D1, Vectorize, Workers AI) plus a “Prompt Capsule” feature for deterministic LLM context.

A collection of computer vision tools and datasets for sports analytics, focusing on challenges like ball tracking, player re-identification, and jersey number OCR.

An open-source implementation of OpenAI's CLIP for training and using large-scale contrastive language-image models.

An AI-powered tool that automatically collects, recognizes, and organizes electronic invoices from emails into categorized folders and Excel reports for reimbursement.

A tutorial‑style, open‑source Python project that shows how to build a modular, agent‑driven Retrieval‑Augmented Generation system with LangGraph, hierarchical chunking, conversation memory, query clarification, multi‑agent map‑reduce, self‑correction, and evaluation via RAGAS. Works with Ollama, OpenAI, Anthropic, Google Gemini, Qdrant vector store, and optional Langfuse observability.

AIKON is a bridge between 2007-era Nokia phones and modern AI models, allowing users to chat with LLMs like Claude and OpenAI on legacy hardware via a custom Go server.

EngineWire is a native Unreal Engine plugin that lets LLM‑based assistants (Claude, Cursor, VS Code, etc.) control the editor through a single MCP tool called `unreal`. It exposes ~400 actions—spawning actors, editing Blueprints, building materials, running Play‑In‑Editor, taking screenshots, and more—via a simple search/describe/execute flow over either a local HTTP server (port 3000) or a Node.js stdio proxy (port 8090). Security is token‑based and localhost‑only by default. Install the plugin, enable the server, add the token to your AI client, and you can issue natural‑language commands that the plugin translates into Unreal‑Editor operations.

A cloud-native vector database that stores objects and vectors to enable semantic search, hybrid search, and retrieval-augmented generation (RAG) at scale.

AutoHunter is an AI‑driven, Docker‑based platform that continuously hunts for web vulnerabilities. It uses LLM‑guided agents (Collector, Worker, Reviewer) together with real tools like nmap, nuclei, and sqlmap. Humans only perform final review. The system supports multiple search engines (FOFA, Quake, Shodan, etc.), offers a Vue dashboard, and persists data in SQLite. It’s licensed Apache 2.0 and intended for authorized security testing.

Chat SDK is a TypeScript library that lets you write a single bot and run it on many chat platforms (Slack, Teams, Discord, etc.) via plug‑in adapters, with built‑in support for AI streaming, rich UI cards, and state management.