Trending AI projects

A local-first control plane and MCP server that allows any LLM to author, edit, and execute ComfyUI workflows using natural language.

A Node.js CLI tool that synchronizes AI development tool configurations by generating tool-specific files from a single, unified source of truth.

A terminal-native AI coding assistant that uses persistent memory and multi-agent orchestration to handle long-horizon software development tasks.

LLM Wiki Agent is a local, agent‑driven system that ingests PDFs, DOCX, markdown, etc., extracts entities and concepts, builds an ever‑growing inter‑linked markdown wiki, flags contradictions, and generates a visual knowledge graph—all without a server or database.

An "Awesome" list of curated AI-in-finance resources: tools, papers, courses, and strategies for automated analysis and trading, organized by category with star ratings for notable entries.

A high-performance programming language with TypeScript-like syntax designed for AI agents, featuring a compiler that provides actionable JSON edits to fix coding errors.

Agent Flow is a real‑time visual debugger for Claude Code and Codex AI agents. It streams execution events via a lightweight hook (Claude) or Codex rollout logs, and displays them as an interactive node‑graph with timeline, transcript, and heat‑map panels. Available as a standalone web app (`npx agent-flow-app`), a VS Code extension, or a dev server, it supports multi‑session tabs, JSONL replay, and runtime selection. Designed to make agent reasoning, tool‑call chains, and performance visible for debugging and prompt‑engineering, it ships with optional anonymous telemetry and is Apache‑2.0 licensed.

MuseAI‑Skills is a snapshot of Muse AI’s skill definitions, configs, and runtime scripts – a reference for agent workflow design, not a full open‑source AI engine.

A framework for creating repeatable AI software development workflows by moving the control plane from prompts to deterministic Python code, featuring gated agent phases and real-time observability.

A curated, community-maintained list of natural language processing resources, covering libraries, datasets, tutorials, research summaries, and language-specific tools. It helps NLP practitioners and learners quickly find high-quality materials across many languages and use cases.

An SDK implementing the MCP Apps standard to enable rich, interactive web interfaces for AI tools over the Model Context Protocol.

A real-time security layer for AI agents that blocks destructive commands, scans plugins for malicious code, and performs daily security audits to prevent data theft and system damage.

OpenGame is an open‑source, Node‑based framework that uses a specialised code LLM (GameCoder‑27B) to generate complete web games from a single natural‑language prompt. It provides a reusable *Game Skill* (template selection + automated debugging), a CLI (`opengame`) for headless generation, and an evaluation suite (OpenGame‑Bench) to measure playability. The system scaffolds projects with engines like Phaser, runs them in a sandbox, fixes integration errors, and outputs a ready‑to‑play HTML/JS game.

Copilot API is an open‑source Node/Bun server that provides a single local OpenAI‑compatible endpoint, routing coding‑assistant requests to GitHub Copilot, built‑in Codex/xAI, or many third‑party model providers. It supports Chat Completions, Responses, and Anthropic Messages, offers streaming via SSE/WebSocket, includes a desktop Electron GUI, Docker deployment, and a CLI for quick start.

A family of tiny neural text-to-speech voices (294k to 2.3M parameters) that run in real-time on $3 microcontrollers or in the browser without cloud dependencies.

Traycer is a cross‑platform desktop app that orchestrates multiple coding LLM agents (e.g., Claude Code, Codex, Copilot) in a shared context, supports agent‑to‑agent communication, and adds real‑time team collaboration features.

A platform for reproducible world model research and evaluation that provides a unified interface for data collection, training, and model-predictive control evaluation.

PlainBacktest is a framework that enables AI agents to translate natural language trading strategies into reproducible, audit-ready backtests with independent ledger reconciliation.

An intelligent customer service agent for robot vacuum users that combines Agentic RAG and device data analysis to provide technical support and personalized usage reports.

A modern, asynchronous web scraping and browser automation library for Python that simplifies data extraction, proxy management, and bot-evasion for reliable crawling.

A Python package for probabilistic record linkage and deduplication that identifies and duplicate records without unique identifiers using unsupervised learning.

NeuroBook is an engineering-focused writing environment that integrates AI agents with structured world-building and plot-tracking tools to help authors write consistent, high-quality long-form fiction.

A session cleaner and prompt injection tool for AI coding assistants that prevents refusals during security testing and CTF competitions.

prime-rl is a framework for large‑scale reinforcement learning, designed for asynchronous RL training at scale. It enables training models on up to 1000+ GPUs with features like FSDP2, vLLM, and support for agentic and multimodal tasks.

Cinema DNA is an AI agent skill that provides a structured framework for designing and generating coherent, narratively driven cinematic storyboards and stills while maintaining visual continuity.

An AI Agent support library for E-language that enables AI to automatically read and edit source code via a local MCP server and integrated IDE tools.

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

A Rust interface for hardware-accelerated inference and training of ONNX machine learning models, enabling efficient deployment across various hardware.

An AI-powered tool to transcribe, summarize, and archive videos and podcasts from 30+ platforms or local files using Faster-Whisper and LLMs.

Better Harness is an open‑source tool that analyses the whole workflow of AI coding agents (Claude Code, Codex, Qoder, Cursor, GitHub Copilot, etc.). It gathers project and session evidence, evaluates five dimensions of the *Agent Work Loop* (task understanding, controlled execution, change validation, reliable delivery, learning capture), and produces a visual HTML report with prioritized, evidence‑backed findings and repair suggestions. Missing evidence is shown explicitly, helping teams improve repeatability, validation, and learning while still benefiting from AI‑generated code.

Halo AI Workstation is an open‑source desktop app that combines a chat‑style AI workbench with autonomous “Digital Humans”—AI agents that can run on schedules, keep memory, and collaborate in distributed teams. It supports multiple LLM back‑ends (Claude, ChatGPT, etc.), offers built‑in document editing, web browsing, terminal control, and integrates with IM platforms (Feishu, WeChat, WeCom) for remote hand‑offs. The software runs locally on macOS, Windows, Linux, and has mobile remote clients, requiring no backend service.

An experimental fork of Windows Terminal that integrates AI agents directly into the command-line interface to provide context-aware assistance, error detection, and command suggestions.

A cross-platform desktop app that uses local or remote AI to categorize files and suggest descriptive filenames for images, documents, and media.

An open-source Metal-based inference engine that runs LLMs quickly on Apple silicon by fusing layer computations into megakernels, using DSpark speculative decoding to amortize costly model passes, and serving an OpenAI-compatible API for local coding agents.

Hycli is a cross‑platform native tool that automatically turns any logged‑in website into a typed command‑line interface and an MCP server, letting AI agents safely read and (with explicit one‑time permission) write to the site. It prepares actions by analysing docs, OpenAPI/GraphQL specs, and live browser traffic, stores credentials locally, and offers a dashboard plus 20‑language UI. Ideal for building autonomous agents or scripting personal web workflows.

Inspect Robots is an open‑source Python framework for defining robotics benchmarks and running any policy—LLM agents, VLAs, scripted scripts—on real robots, simulators, or a mock world. It logs full sensor streams, policy transcripts, and scores, and offers live Rerun visualisation. Plugins add support for specific robots (YAM, Franka, etc.) and backends (ROS, Isaac Sim). The core is lightweight (NumPy only) with optional extras for visualization, LLM agents, code‑as‑policy, and voice input.

An open-source Android LLM client that lets users use their own API keys to access multiple AI providers and local models with agentic tools and local storage.

A macOS application for discovering, organizing, and editing AI coding agent skills and agents across multiple tools like Claude Code, Cursor, and Windsurf.

A collection of 27 AI agent skills for Codex and Claude Code to help scientists write, revise, and manage rebuttals for Nature-series life science and computational biology papers.

A typeface and encoding system that protects written work by serving decoy text to AI scrapers while rendering the original words for human readers.

BiRefNet is a high-resolution dichotomous image segmentation tool that provides state-of-the-art precision for separating foreground objects from backgrounds in high-resolution images.

A desktop application that translates books and documents of any length using local or cloud-based LLMs while preserving original formatting and document structure.

MCPJam Inspector is an open‑source platform for testing, debugging, and evaluating MCP (Model‑Control‑Protocol) servers that power AI assistants. It offers a web/desktop/CLI UI to run your server against 16 LLM client configurations, inspect JSON‑RPC traces, debug OAuth flows, define eval test cases, share workspaces, and integrate into CI/CD. Licensed under Apache 2.0.

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 free, open-source transcription app that converts speech to text locally on your computer using various AI models for privacy and speed.

A comprehensive toolkit for traditional divination that automates complex chart calculations and provides structured prompts for LLM interpretation via API, MCP, and agent skills.

A Windows AI upscaler that enhances, upscales, and de-noises images and videos locally using DirectX12 compatible GPUs.

OpenDeepWiki converts Git repos, ZIP archives, or local directories into AI-generated knowledge bases, providing structured docs, a searchable public site, chat, and MCP endpoints. It automates documentation creation and keeps it updated via background workers.