Dograh AI is an open‑source, self‑hostable platform for building and testing voice conversational agents. It provides a visual workflow editor, telephony integrations (Twilio, Vonage, etc.), and a modular LLM/STT/TTS stack that you can replace with any provider. One‑command Docker setup gets the whole system running locally, and Python/Node SDKs let you create agents programmatically. The project is BSD‑2 licensed and backed by a Slack community.

A multi-node vLLM inference setup for Qwen3.8-Flash-Next optimized for two NVIDIA DGX Spark nodes, supporting NVFP4/FP8 quantization and context windows up to 1M tokens.

An AI-powered investment decision system that simulates a committee of 18 legendary investors to provide consensus analysis, position sizing, and structured debates on stocks.

A privacy-first CLI for semantic code search that uses vector embeddings to find code by meaning rather than exact text, reducing token usage for AI agents.

Proma is an open‑source, cross‑platform desktop AI agent that combines chat, planning, project‑based memory, and embedded tools (browser, terminal, calendar, Obsidian‑style markdown editor). It supports parallel sub‑sessions, skill bundles, and remote connectors (Slack, WeChat, etc.). Installable via binaries for macOS, Windows, and Linux; the open‑source edition requires user‑provided LLM APIs, while a commercial edition adds hosted model access, team management, and extra services. Licensed under AGPL‑3.0 with optional commercial licensing.

A comprehensive AI content creation skill for WeChat Official Accounts that automates topic selection, evidence-based writing, editorial review, and professional layout formatting.

A compact, human-readable encoding of the JSON data model designed to minimize token usage in LLM prompts while maintaining high retrieval accuracy.

An enterprise AI digital employee platform that provides orchestration, deployment, and runtime capabilities for AI agents with support for on-premise deployment.

Open Cowork is a free, open‑source desktop app that wraps Claude‑style (and other) LLMs into a local AI‑agent workspace. With one‑click installers for Windows/macOS, VM‑level sandboxing (WSL2/Lima), a built‑in “Skills” system for generating PPTX/DOCX/PDF/XLSX files, MCP connectors for browsers/Notion, and remote control via Feishu or Slack, it lets non‑technical users give natural‑language commands that read/write files, automate GUI apps, and produce professional documents—all running locally with optional VM isolation.

An open-source relational database that provides MySQL compatibility and advanced features like native vector search and pluggable storage engines.

A step-by-step educational project that implements a minimal coding agent from scratch in TypeScript and Python to explain the architecture of AI coding assistants.

A multi-platform package manager and inference UI for Stable Diffusion that provides one-click installation and shared model management for various AI image generation interfaces.

A network traffic capture and analysis tool that uses AI to automate protocol reverse engineering and API documentation from browsers, apps, and devices.

Peekaboo is a macOS‑only CLI and menu‑bar app that captures the screen, reads the accessibility tree, and performs native UI actions (click, type, press, etc.). It includes an LLM‑driven “agent” that can translate natural‑language instructions into sequences of these commands, and it can be exposed to external AI clients via a Model‑Control‑Protocol (MCP). Install via Homebrew, npm, or a signed DMG; configure model providers in `~/.peekaboo`. Ideal for GUI automation, testing, and building AI agents that control the desktop.

A command center for AI coding agents that allows users to manage, orchestrate, and switch between multiple agent sessions across different projects in one terminal.

MLX‑Audio is a Python (and optional Swift) library that runs a large collection of modern speech‑to‑text, text‑to‑speech, speech‑to‑speech, voice‑cloning, VAD/diarization, and music‑generation models on Apple’s MLX framework. It provides CLI tools, a Python API, a web UI, and an OpenAI‑compatible REST endpoint, with support for 3‑ to 8‑bit quantisation to fit big models on M‑series chips.

A metasearch library that aggregates results from multiple web search services and provides content extraction tools for text, images, videos, and news.

A GPU-accelerated version of the MuJoCo physics simulator designed for NVIDIA hardware to provide high-throughput, accurate simulation for robotics research.

An open-source, self-hosted ERP for construction project management that provides tools for BOQ, BIM/CAD takeoff, 4D scheduling, and 5D cost modeling.

A plugin for OpenCode that adds a long-running goal mode, allowing AI coding agents to maintain focus on a specific objective with persistent state and automatic continuation.

An extensible quantitative finance framework that integrates data collection, factor mining, machine learning, and backtesting for quantitative investment research.

A capability and harness library for Pydantic AI that provides modular blocks for building long-running, autonomous agents with memory, planning, and safe execution environments.

A minimal harness that gives LLM agents raw primitives to control macOS applications, browsers, and files without requiring app-specific tools.

A collection of reference implementations and starter projects for building applications with the Claude API, covering agentic workflows, computer use, and browser automation.

A comprehensive library of 120 AI agent skills and plugins that act as a virtual marketing staff across seven disciplines including SEO, social media, and product launches.

FastWAM is a high-performance World Action Model for robotics that enables fast action prediction by optionally skipping test-time future imagination, significantly reducing inference latency.

A Godot-based life simulation game where residents are autonomous LLM-powered agents who make decisions, form relationships, and remember experiences based on their personalities and environment.

An open-source face recognition SDK for Windows and Linux that provides on-premise face detection, landmark detection, and similarity comparison using deep learning.

A hardware-aware LLM recommendation tool that ranks the best HuggingFace models based on your specific GPU/CPU/RAM and real-world benchmark performance.

An AI operations agent that automates infrastructure root cause analysis and remediation, accessible via Slack or Telegram.

A native macOS sticky note app with a fanning deck UI that lives at the screen edge for quick, unobtrusive note-taking.

An open-source, AI-native knowledge base and Evernote alternative that offers self-hosting, multi-device sync, and deep AI agent integration via MCP.

A real-time audio translation tool for Windows 11 that integrates Windows Live Captions with LLM and traditional translation APIs to provide translated subtitles via a transparent overlay.

A library of 103 opinionated Claude Skills for the full web lifecycle, providing standardized frameworks for brand strategy, design, SEO, and development.

An AI agent that automates the creation of professional presentations, transforming prompts and documents into fully formatted PPTX files using a dedicated toolset and fine-tuned models.

MoGe is a model for recovering accurate 3D geometry, including metric depth and point maps, from single open-domain images.

A local application for writing long-form fiction with AI that helps authors manage plot outlines, world-building knowledge, and narrative consistency across chapters.

A specialized Claude Code workspace that automates research, writing, and optimization of long-form SEO content and landing pages using data-driven analysis and AI agents.

A flight and hotel search and booking engine designed for AI agents and developers, providing wholesale prices without tracking-based price inflation.

An autonomous offensive security framework that automates bug bounty hunting and vulnerability research using an AI agent or MCP server integration.

A Docker-based deployment framework for vLLM optimized for NVIDIA DGX Spark, enabling high-performance single-node and multi-node cluster inference.

XRAG is an open‑source Python framework that benchmarks the individual components of Retrieval‑Augmented Generation (RAG) pipelines. It offers modular plug‑ins for retrievers, embeddings, LLMs, and orchestrators, supports traditional IR metrics plus LLM‑based quality scores, provides a CLI (`xrag-cli`) and a Web UI, and can run as a REST service. Install via PyPI, configure with `config.toml`, and use commands like `xrag-cli run`, `xrag-cli webui`, or `xrag-cli api` to evaluate or serve RAG systems.

A lightweight system that helps developers align AI agents with their codebase's specific standards and patterns to ensure consistent, high-quality builds.

An orchestration-builder SDK for multi-agent coding workflows that provides configurable infrastructure for work routing, runtime providers, and state reconciliation.

A Codex Skill that converts reference images or AI-generated diagrams into native, editable Microsoft Visio (.vsdx) files for scientific paper figures.

An AI agent plugin for Obsidian that enables multi-step research and knowledge work by integrating LLMs directly into the user's vault.

A Windows task‑bar widget that locally tracks how much of your daily/monthly quota you’ve used on AI code‑generation services (Claude Code, Codex, Google Antigravity, OpenCode Go, Cursor) and shows when the limits reset. Install via WinGet or a direct download, configure providers in a simple dashboard, and enjoy privacy‑first monitoring without any telemetry.

ContextForge is an open‑source gateway that federates MCP, A2A, REST and gRPC services into a single, centrally governed endpoint for AI agents and tools. It provides auth, rate‑limiting, OpenTelemetry tracing, a plug‑in system, and an admin UI, and can be run via PyPI, Docker, or Helm.