Trending AI projects

A non-official SDK and CLI for WeChat Reading that enables over 40 read-write operations, including book management, note synchronization, and public account feed exports.

The official OpenAI Go library provides a type-safe, idiomatic way to integrate OpenAI's models into Go applications, supporting features like streaming, tool calling, and structured outputs.

A local-first meeting notes app for macOS that records, transcribes, and summarizes meetings by combining user notes with audio transcripts, emphasizing privacy and on-device processing.

A local MCP server for agent literature work. The differentiator is original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. The working loop is paper ID → outline → one section → citations. Search is optional.

TAKT is a Node‑JS CLI that orchestrates AI coding agents (Claude, Codex, Cursor, etc.) via declarative YAML workflows. It runs each step in isolated Git worktrees, enforces review/fix loops, logs every action, and can auto‑create PRs. Designed to make AI‑driven development repeatable, auditable, and less dependent on fragile prompts.

A bilingual library of 146 marketing and business skills that enables AI agents to execute complex, multi-step marketing workflows, campaigns, and operational tasks through standardized, prompt-driven SOPs.

A production-ready Rust framework (43 crates, 500K+ downloads) for building AI agents that work with many LLM providers, featuring tools, workflows, graphs, teams, realtime voice, coding agents, governance, and HTTP serving. Currently at 2.3.0 published, with 3.0.0 as an unpublished release candidate adding breaking changes.

Shimmy is a high-performance, single-binary local inference server for GGUF models that provides an OpenAI-compatible API without requiring Python or C++ dependencies.

A serverless runtime for AI workloads that allows developers to deploy and scale AI applications with zero infrastructure overhead and fast cold starts.

A collection of modular automation skills that extend AI coding agents like Claude Code and Cursor with business capabilities like SEO, market research, and asset creation.

OpenAnt (knostic/OpenAnt) is a genuine open-source software project that applies LLMs to security: it scans code repositories to find and verify vulnerabilities, and can generate and vet trusted patches. It's a practical, system-level tool with a CLI, configurable LLM adapters, and a web UI — not a list or tutorial.

Golem is a distributed cloud environment for running WebAssembly components, enabling developers to build and deploy scalable agents in languages like Rust and TypeScript.

A desktop AI writing system for long-form fiction that uses structured memory and local semantic search to maintain narrative consistency across chapters.

A job search system that identifies real versus ghost listings by crawling company career sites directly and using embeddings for local, privacy-preserving search.

A lightweight inference engine for GPT-SoVITS that optimizes speech synthesis for high-speed CPU performance and low memory usage.

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.

A lossless context management plugin for Hermes Agent that uses a SQLite-backed DAG engine to preserve raw conversation history and provide tools for precise memory recall.

VelaTerm is an Agentic Development Environment that manages multiple AI coding agents, terminal sessions, and complex multi-agent workflows within a unified, cross-platform workspace.

A collection of standardized evaluation frameworks for measuring the capabilities of frontier AI models across software engineering, academic research, and smart contract security.

Agent‑Skills is a Node‑JS CLI that adds AI‑assistant‑driven test‑automation “skills” (Selenium, Playwright, Cypress, etc.) for the TestMu AI cloud platform, letting LLMs generate and run tests directly on the service.

Datus is an open‑source Python agent that uses LLMs to automate data‑engineering tasks—semantic modeling, SQL generation, ETL pipeline creation, and report/dashboard building—while storing each interaction in a context engine that improves accuracy over time. It offers a CLI, web chat, and API, integrates with many databases, LLM providers, schedulers and BI tools, and is extensible via a plug‑in system.

A plugin that provides Claude with direct access to 183 cybersecurity and OSINT tools, automatically managing their execution via Docker or native environments.

A Claude Code plugin that uses the Balanced Coupling model to analyze and design modular software architectures to prevent technical debt and coupling imbalances.

An MCP expansion and AI editor toolset for Unreal Engine 5.8+ that enables AI agents to perform deep world-building, animation, and performance profiling within the editor.

A Java library for building stateful, multi-agent AI applications using cyclical graphs, designed to integrate with LangChain4j and Spring AI.

A high-performance, compact vector search and clustering engine that offers faster indexing and lower memory usage than FAISS, with support for multiple languages and disk-based index serving.

A collection of standardized, modular skills and documentation tools designed to help AI coding agents perform Kotlin-specific development tasks more effectively.

DefenseClaw is a security governance framework for AI coding agents that provides runtime traffic inspection, capability scanning, and audit logging to help organizations manage agent risks.

A collection of step-by-step playbooks for setting up AI/ML workloads on NVIDIA DGX Spark devices (Blackwell architecture). Each playbook covers prerequisites, instructions, troubleshooting, and example code, covering topics like model serving, fine-tuning, distributed setups, development environments, and system management.

A proxy server that exposes an Anthropic-compatible API backed by Antigravity's Cloud Code, enabling the use of Claude and Gemini models with the Claude Code CLI.

A command line tool and VS Code extension for versioning data and ML models, tracking experiments, and managing reproducible ML pipelines.

A mobile AI gateway that runs a Linux environment on Android to enable AI agents to control device hardware like cameras, sensors, and location services.

NVIDIA‑labs Object Oriented Agents (NOOA) is a Python‑first, model‑agnostic framework that lets you define AI agents as ordinary classes. Typed fields hold state, regular methods run deterministic code, and methods with `...` bodies are filled in at runtime by an LLM using the method signature and docstring as the prompt. The library includes static validation, optional memory and CLI packages, and automatic tracing. Install via `uv add nooa` (or pip), pick any LiteLLM‑compatible model, define an agent class, and call its generation methods. Safety requires sandboxing because generated code can run arbitrarily. Ideal for rapid prototyping, research, and integrating LLM‑driven agents into existing Python projects.

A self-hosted personal AI OS that integrates persistent memory, task automation, and coding agents across multiple apps and interfaces.

OpenTabs is a CLI‑plus‑Chrome‑extension toolkit that lets LLM agents call real web APIs (Slack, Discord, GitHub, etc.) using the user’s existing browser session, with a library of ready‑made plugins, local‑only execution, and a permission‑based security model.

A curated collection of agentic skills based on an open standard that provides AI coding assistants with expert-level, production-ready knowledge of Azure services.

An AI-powered Zi Wei Dou Shu astrology tool that uses a Python rule engine for precise chart casting and an LLM for human-like interpretation and visualization.

A bundle of six AI agent skills designed to assist job seekers with everything from job discovery and resume tailoring to interview prep and salary negotiation.

A tool that allows developers to copy UI elements from a browser and provide AI agents with the exact source code location and component stack.

A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

An agentic toolkit for n8n that enables building, editing, and deploying workflows as code using VS Code, Cursor, and AI agents with live environment context.

ShipSwift is an AI-native SwiftUI component library that provides production-ready code, animations, and modules to help AI assistants build real iOS applications without guessing.

BuilderIO / skills is a plug‑in catalog that adds ready‑made slash‑commands (e.g., `/factory‑collect`, `/visual‑plan`, `/rewind`) to LLM agents. The skills let agents safely read from Slack, GitHub, Sentry, local UI, etc., generate visual plans/recaps, enforce policy‑gated PR workflows, and keep expensive models in the loop only for high‑level judgment. Install via `npx @agent-native/skills@latest add`, then invoke commands inside any supported agent (Claude, Codex, ChatGPT, etc.).

A UI framework providing enterprise-level components and SDKs for building AI-driven interfaces, specifically optimized for LLM streaming and dynamic interaction.

An AR diffusion framework for robot control that unifies visual world modeling and action inference to improve long-horizon performance and generalization.

An open-source pipeline that automates YouTube video editing by turning raw talking-head recordings into polished videos with AI-generated visuals, audio cleaning, and automated uploads.

Make Comics is an open-source web app that uses AI to generate comic book stories, characters, and panels. It combines image generation and language models to produce coherent visual narratives with consistent character appearances.

A set of AI-compatible skills that enable coding assistants to autonomously control compilers, debuggers, and communication buses for embedded hardware development.