A cloud-native broker that bridges AI coding agents to chat platforms like Discord and Slack using the Agent Client Protocol.

Open‑source library of reusable “skills” that teach AI coding assistants (Claude Code, Copilot CLI, Cursor, etc.) how to work with Elasticsearch, Kibana, Elastic Cloud, Observability, and Security. Install via the `skills` CLI or native plugin systems; each skill is a self‑contained folder with metadata and step‑by‑step API instructions. Designed for safe, credential‑aware automation of Elastic‑stack tasks.

51mazi is an open‑source desktop novel‑writing app (Electron + Vue 3) that offers a rich‑text editor, password‑protected multi‑book management, map drawing, relationship graphs, timelines, and AI‑powered generation of covers, character portraits, scene images, name suggestions, polishing and continuation of text. All data stays local; AI features require DeepSeek and Tongyi Wansxiang API keys.

An open-source data middle platform for enterprise data governance and development, featuring ETL, metadata management, and AI-powered Text2SQL data Q&A.

AgentPet is a cross‑platform desktop app that monitors the live state of AI coding agents and gamifies the experience with a tamagotchi‑style pet that levels up based on token usage and completed sessions. It works offline, supports many agents, offers per‑project dashboards, and provides optional web sync and leaderboards.

A high-performance, open-source search database that provides full-text, vector, and hybrid search capabilities as a fast alternative to Elasticsearch.

A command-line utility for performing forced alignment of speech datasets, synchronizing audio recordings with their text transcripts using Kaldi.

TornadoVM is an open‑source Java runtime that JIT‑compiles Java bytecode into GPU kernels (CUDA, OpenCL, Metal) and integrates NVIDIA libraries (cuBLAS, cuFFT, cuDNN) and Tensor‑Core intrinsics. It lets you write kernels in pure Java, build task graphs, and run them on NVIDIA, AMD, Intel, Apple‑Silicon GPUs or CPUs. Used for LLM inference (GPULlama3.java), ray‑tracing, and scientific pipelines, it is installable via SDKMAN! and available on Maven Central under Apache 2.0 (API) and GPLv2 + Classpath Exception (runtime).

A Claude Code plugin that implements an iterative development loop with independent AI review to ensure high-quality, bug-free code.

A media automation tool that analyzes watch history from Plex, Jellyfin, or Emby to automatically suggest and request similar content via Seer, featuring AI-powered recommendations and natural language search.

An AI-powered OSINT tool that automates the gathering of unstructured news from various sources and uses NLP to help analysts create structured intelligence reports.

A web-based interface for Music-Source-Separation-Training that allows users to isolate vocals and instruments from music tracks using various AI models.

A cross-platform image generation and editing client that prevents connection timeouts during long inference tasks using SSE and WebSocket modes.

An AI-powered cybersecurity automation tool that streamlines vulnerability scanning, penetration testing, and security auditing through an LLM-driven CLI agent.

A lightweight cross-platform IDE designed for AI programming that integrates AI agent sessions, multi-project management, and Git workflows into one interface.

An intelligent terminal assistant for tmux that observes pane content and executes commands to act as a context-aware pair programmer.

A ROS 2 wrapper for RTAB-Map that provides graph-based SLAM with appearance-based loop closure detection to build 3D maps from RGB-D, stereo, or lidar data.

A code-first, model-agnostic toolkit for building, evaluating, and deploying sophisticated AI agents and multi-agent systems.

A tool for creating digital personas of former partners by analyzing chat histories and personality traits to simulate their specific tone and emotional patterns.

A pure C implementation of an AI assistant for the ESP32-S3 chip, providing a low-power, always-on agent with local memory and tool-calling capabilities via Telegram.

An open-source framework for training language agents with reinforcement learning, allowing the same agent code to be used across different backends, sandboxes, and benchmarks.

A Python package for estimating heterogeneous treatment effects from observational data by combining machine learning with econometrics for automated causal inference.

An enterprise AI agent platform that transforms internal data and domain expertise into secure, autonomous digital employees capable of delivering finished business artifacts.

An OCR-powered screen-capture tool for Linux, macOS, and Windows that extracts text and barcodes from the screen instead of saving images.

An OpenVINO-powered inference engine for Intel devices that serves LLMs, VLMs, and audio models via OpenAI-compatible endpoints.

Cache‑DiT is a PyTorch‑native inference engine that accelerates diffusion‑transformer (DiT) models with hybrid activation caching, various parallelism strategies, optional 8‑/4‑bit quantization, and CPU layer‑offload. It supports 40+ DiT families (image, video, audio, 3‑D) from Hugging Face Diffusers and integrates with tools like ComfyUI, SGLang, vLLM‑Omni, TensorRT‑LLM, and Jetson containers.

A high-performance serving stack for DeepSeek-V4-Flash on NVIDIA DGX Spark, featuring continuous batching, speculative decoding, and a memory governor for massive context windows.

A durable memory system for coding agents that records session events to a local log and allows agents to search for relevant prior context to handle long-horizon tasks.

Aliyun Model Studio CLI (bailian‑cli) is a terminal tool for Alibaba Cloud’s AI platform, providing commands for multimodal generation (text, image, video, speech), asset understanding, managed‑agent orchestration, dataset validation, fine‑tuning, deployment, and account management. Install via npm or a one‑line script, authenticate with an API key or OAuth, then issue `bl …` commands or let an AI Agent translate natural‑language prompts into CLI calls.

A C++ implementation of the DDS standard that provides high-performance, real-time publisher-subscriber communication for distributed systems and robotics.

A synthetic environment generation pipeline that creates thousands of SQL-backed tool-use environments for large-scale agentic reinforcement learning.

PointWorld is a large pre-trained 3D world model that predicts full-scene 3D point flows from partial RGB-D captures and robot actions to improve in-the-wild robotic manipulation.

An open-source agentic IDE for web developers that integrates a coding agent with direct access to the browser's console and debugger for real-time building and browsing.

A deterministic, pattern-based humanizer that rewrites AI-sounding text into natural language across four languages while strictly preserving factual meaning.

An open-source desktop control console that provides a visual workspace and unified management for local AI coding agents.

A modern intelligent dialogue system that enables the creation and management of AI agents with multi-agent collaboration, RAG, and a three-layer memory architecture.

A local-first AI image generation workbench that unifies GPT Image and Gemini with integrated asset libraries, prompt templates, and task management.

A Model Context Protocol (MCP) plugin that connects AI clients to over 9,000 apps, enabling AI assistants to trigger workflows and pull data using plain English.

The official JavaScript/TypeScript SDK for LM Studio, enabling developers to integrate local LLMs into applications with advanced memory and hardware controls.

A collection of CLI tools, plugins, and agents designed to enhance the productivity and capabilities of Claude Code and other AI coding agents.

An OCR tool specifically optimized for Japanese manga, capable of recognizing multi-line text, furigana, and both vertical and horizontal layouts.

A Ghidra extension that implements the Model Context Protocol (MCP), enabling AI assistants to programmatically interact with Ghidra's reverse engineering capabilities.

An Android app for manga translation that uses local bubble detection and OCR combined with LLM-based translation to overlay translated text on original images.

An AI-powered threat modeling tool that uses LLMs to generate STRIDE-based threat models, attack trees, and mitigations for traditional and AI-driven applications.

A Chrome extension that adds a native AI layer to the browser, integrating multiple LLM providers and enabling agentic browser control and external MCP tool support.

A Bun and TypeScript-based AI agent for nutrition and healthy diet support featuring RAG, food image analysis, and official health data synchronization.

codedb is a zero‑dependency, Zig‑based server that builds rich indexes (trigram, word, symbol, call‑graph) of a local codebase and exposes them via the Model Context Protocol (JSON‑RPC over stdio). AI coding assistants (Claude Code, Cursor, Gemini CLI, etc.) can query for file trees, outlines, symbol definitions, callers, and full‑text search in sub‑millisecond latency, dramatically reducing token usage. It runs as an MCP daemon (`codedb mcp`) or an HTTP server, updates incrementally via a file watcher, and ships signed binaries for macOS, Linux, and Windows.

A Python wrapper for ByteDance's Seedance 2.5 API that enables the generation of high-fidelity AI videos with realistic human faces and consistent character identities.