A 100% private, offline AI voice assistant that provides conversational awareness and unlimited local memory, integrating with thousands of tools via MCP.

A geospatial analysis skill for AI agents that enables natural language querying of PostGIS, BigQuery, and Snowflake, featuring a visual map-in-the-loop feedback system for self-correction.

A CLI text-to-speech tool using the Kokoro model that converts text, PDFs, and EPUBs into natural-sounding speech with support for voice blending and streaming.

A family of pretrained foundation models for zero-shot time series forecasting that treats time series data as tokens for language model architectures.

A local application that converts video audio into multilingual subtitles using whisper.cpp for transcription and Hy-MT2 or cloud APIs for translation.

CraftGRN is a modular framework that integrates ATAC-seq and RNA-seq data to infer condition-specific transcription factor binding sites and reconstruct dynamic gene regulatory networks.

Ouroboros is a self-evolving AI agent with durable memory and a continuous identity that can rewrite its own code and coordinate specialist agent swarms.

NumPy is the fundamental package for scientific computing with Python, providing N-dimensional array objects and tools for linear algebra and Fourier transforms.

ArduPilot is a comprehensive open-source autopilot software suite that provides advanced control for a variety of unmanned vehicles, including drones, planes, and submarines.

A command-line interface for Z-Library that enables searching and downloading books, managing mirror domains, and sending files to Kindle.

A research prototype for co-authoring durable technical documents like RFCs and implementation plans using repository-grounded AI agents.

Zero-WAM is a robotic manipulation framework that enables zero-shot task generalization by using human demonstration videos and language as in-context prompts to predict robot actions.

A htop-like task monitor for GPUs and AI accelerators that provides real-time visual monitoring of utilization, temperature, and power across multiple hardware vendors.

A local MCP server that enables AI agents to perform deep literature research on arXiv, featuring section-level LaTeX reading, citation tracking, and topic monitoring.

An MCP server that brings Firecrawl's web scraping, searching, and browser interaction capabilities to AI agents for clean, structured web context.

An open-source toolkit for optimizing and deploying deep learning models across CPU, GPU, and NPU hardware to boost inference performance.

Pixal3D is a high-fidelity 3D asset generator that creates detailed geometry and PBR textures from a single image or multiple views using pixel-aligned back-projection.

An open-source security layer that provides antivirus-style runtime protection for AI agents, blocking risky actions like secret leaks and unsafe commands.

CLI Printing Press is a Go‑based generator that, using Claude Code (or Codex), turns any API or website into a token‑efficient Go CLI plus a matching MCP server. It automatically researches docs, scrapes traffic, builds a local SQLite data layer, adds compound analytics commands, verifies the output, and can publish the result to a public library. Install via a single script, then invoke `/printing-press <api>` inside an AI‑assistant session to get a ready‑to‑use CLI (e.g., ESPN, flight‑goat, linear‑pp-cli) that works offline, outputs compact JSON, and is optimized for AI agents.

A self-hosted platform for managing AI agents across multiple devices, featuring a task board and an open API for business workflow integration.

An open-source platform that integrates multiple AI agents into team communication tools like Slack and GitHub, enabling collaborative multi-agent workflows.

An AI-powered research assistant that performs deep, agentic research using local LLMs and multiple search engines to generate cited reports from the web and personal documents.

A toolkit that enables AI agents to read, build, edit, and test Simulink models by providing MCP tools and domain-specific skills based on Model-Based Design best practices.

An automatic hyperparameter optimization framework for machine learning that uses a define-by-run API to efficiently find optimal model parameters.

A coding agent that automates browser interactions by writing and execute JavaScript via the Chrome DevTools Protocol, allowing it to adapt to any website at runtime.

Codex Proxy is a local service (desktop app, lightweight “no‑node” zip, or Docker container) that converts the Codex Desktop Responses API into standard OpenAI, Anthropic, Gemini, and Ollama endpoints. After logging in with a ChatGPT account, it issues a local API key; any client that understands the usual `/v1/chat/completions` or `/v1/messages` format can call Codex, with full support for streaming, function/tool calling, structured outputs, image generation, multi‑account rotation, and TLS fingerprint spoofing.

Kong is a cloud-native API and AI gateway that centralizes routing, security, and orchestration for microservices, LLMs, and Model Context Protocol (MCP) traffic.

An offline Structure-from-Motion system for video that estimates camera poses and 3D maps by exploiting temporal tracks, loop closures, and metric depth.

A bimanual robotic manipulation platform that provides a scalable data generator and benchmark for training and evaluating robust dual-arm robot policies.

Stirrup is a lightweight Python framework for building LLM‑driven agents. It supplies ready‑made tools (code execution, web search, file I/O, multimodal handling) and a flexible `Tool`/`ToolProvider` system, while automatically managing context limits and session lifecycles. Install via `pip install stirrup` (optional extras for Docker, browsers, etc.), create a client (OpenRouter, LiteLLM, or any OpenAI‑compatible API), instantiate an `Agent`, and run a session that lets the model invoke tools to solve tasks. Custom tools and providers are easy to add, making Stirrup suitable for rapid prototyping, domain‑specific assistants, and research on tool‑using agents.

A completely offline voice-to-text input tool for Windows that enables low-latency, push-to-talk typing and file transcription using local ASR models.

DeepSWE is a benchmark for measuring coding agents on 113 long-horizon software engineering tasks from real-world open-source repositories.

A data layer for AI systems that converts documentation, codebases, and videos into structured knowledge assets for AI skills, RAG pipelines, and coding assistants.

An open-source enterprise AI development platform that integrates cloud development environments, AI task management, and project requirement tracking for professional engineering teams.

A web-based workstation surface that serves your local computer's files, terminal, and git state to any browser, featuring integrated AI agents for machine automation.

A web scraping and browser automation library for Python that provides tools to build reliable, human-like scrapers that bypass bot protections.

A high-performance communication library for MoE models that provides optimized GPU kernels for expert parallelism to maximize throughput and minimize SM resource usage.

An open-source multi-agent framework for simulating large-scale agent societies to study scaling laws, emergent behaviors, and synthetic data generation.

A local-first routing skill for Codex that separates high-level planning and adjudication by Claude Fable 5.1 from code implementation by specialized OpenCode Go agents.

YOLOv5 is a PyTorch‑based, open‑source object detection/segmentation/classification model suite from Ultralytics, offering multiple model sizes, simple Python/CLI inference, one‑line training, and export to many deployment formats.

An interactive visualization tool that runs a live GPT-2 model in the browser to help users learn how Transformer-based models predict text.

A local-first AI presentation generator that creates editable HTML slides from prompts or documents and supports high-fidelity import/export of PPTX files.

A TypeScript framework for building and shipping MCP servers and interactive AI apps with native React views and built-in debugging tools.

An all-in-one AI content operations workspace for social media creators that integrates viral content collection, automated research, and scheduled AI content generation.

A lightweight AI agent runtime written in Go that allows users to create, manage, and deploy multi-agent systems with isolated sandboxes and multi-channel support.

An open-source orchestration framework for real-time digital-human conversations, integrating LLMs, TTS, STT, and video rendering via WebRTC.

An AI-powered relationship analysis tool that processes WeChat and QQ chat logs to quantify romantic dynamics using psychological frameworks.

A library of structured engineering skills for AI agents that replaces generic AI outputs with disciplined habits like systematic debugging and design pressure-testing.