A CLI tool that converts websites into a compact, numbered format for AI agents to browse the web without burning excessive tokens.

An open-source research framework for universal metric 3D reconstruction that uses a single transformer model to handle multiple 3D tasks from various input combinations.

An AI-powered workbench for FreeCAD that generates and executes Python code to create 3D models from natural language descriptions.

ExecuTorch is an open‑source PyTorch‑based runtime for deploying AI models on edge devices—from phones to micro‑controllers. It exports models directly from PyTorch, compiles them ahead‑of‑time into a tiny `.pte` file, and runs them on a variety of hardware back‑ends via lightweight C++/Python/Swift/Kotlin APIs. It supports vision, speech, and LLMs (e.g., Llama) and is used in Meta’s production apps.

A fast, flexible LLM inference engine written in Rust that supports multimodal models, agentic tool execution, and OpenAI/Anthropic compatible APIs.

A comprehensive toolkit of 70+ custom nodes for ComfyUI designed for professional image production, specializing in batch processing, automated ID photo creation, and advanced mask manipulation.

An AI-powered voice input method for Android that supports multiple cloud and local ASR engines with LLM-based text post-processing.

An open-source, local-first diagramming studio that combines a visual canvas with bidirectional diagram-as-code and AI generation to create technical architecture flows.

A serverless Web SSH terminal based on Cloudflare Workers that allows users to manage remote servers directly from a browser with built-in SFTP and AI assistance.

An LLM-first SEO analysis toolkit for AI IDEs that uses 89 scripts and 10 specialist agents to automate technical SEO audits and strategic planning.

OpenAI’s gpt‑oss repo delivers reference code and tooling for the open‑weight 120 B and 20 B LLMs, including a special Harmony chat format, MXFP4 quantization, and back‑ends for PyTorch, Triton, Metal, vLLM, Ollama, and more. Licensed Apache‑2.0, it’s aimed at researchers and developers who want to run, fine‑tune, or build tool‑augmented agents with these models.

An AI-powered companion for paperless-ngx that automates document titling, tagging, and metadata extraction using LLMs and advanced OCR providers.

Maid is an open‑source Android app (React Native) that lets you run GGUF LLMs locally via llama.cpp and connect to many remote LLM APIs. It offers one‑tap model downloads, chat management, adjustable generation settings, optional cloud sync, and a companion TTS app (Maise). Install from GitHub releases or Google Play, or build the APK yourself.

A security-focused proxy for MCP servers that allows AI agents to scale beyond tool limits and reduce token costs through on-demand tool discovery.

A compact, open-source text-to-speech synthesizer using formant synthesis to support over 100 languages with a very small memory footprint.

An open-source GUI for yt-dlp that provides video downloading from 1,800+ sites with integrated AI video summaries, natural language editing, and AI-powered subtitle generation.

A TypeScript and JavaScript SDK that makes functions durable by persisting progress, retrying failed steps, and allowing workflows to suspend without using compute.

A compiler that turns raw sources into a structured, citation-traceable Markdown wiki, moving knowledge extraction from query-time to compile-time for better agent and human retrieval.

A GPU-accelerated MediaPipe plugin for TouchDesigner that enables real-time computer vision tasks like pose and hand tracking without requiring external installations.

A zero-dependency Python CLI and AI agent skill that enables image generation using ChatGPT or Gemini subscriptions without requiring an OpenAI API key.

A cross-platform AI chatting application that provides advanced tools for roleplay, including multiple API support, long-term memory systems, and immersive visual assets.

An open-source Android document scanner that uses local machine learning for automatic document detection and perspective correction to create private PDFs.

A benchmark for measuring whether AI models can detect and reject nonsense premises in questions instead of confidently accepting invalid assumptions.

A scalable Kubernetes scheduler that optimizes GPU resource allocation and fairness for large-scale AI and machine learning workloads.

An open-source, AI-native alternative to Render that allows developers and coding agents to deploy applications from Git to HTTPS on self-owned infrastructure.

A tmux-native TUI workspace for managing multiple terminal AI agents, allowing users to preview conversation history and jump between sessions quickly.

An open-source SDK for deploying real-time interactive AI avatars on mobile and embedded devices with low latency and on-device execution.

Open‑source MCP (Model Context Protocol) servers that let LLM‑powered tools fetch live AWS documentation, IaC guidance, and safely invoke AWS APIs. Includes managed remote servers and local binaries for docs, IaC, EKS, etc., all accessed via a stdio‑based protocol.

Argos Translate is an open‑source Python library for offline neural‑machine translation. It downloads pre‑trained OpenNMT models packaged as ".argosmodel" files, supports pivoting through intermediate languages, offers GPU acceleration via CTranslate2, and can be used via a Python API, CLI, or a separate desktop GUI. The project also powers the LibreTranslate web/API service.

DocETL is a declarative and agentic framework for processing large-scale structured and unstructured data using LLMs, automating the optimization of prompts and models for cost and accuracy.

A C++ 17 library for creating Behavior Trees to manage complex decision-making in robotics and game AI, offering a reactive and flexible alternative to Finite State Machines.

HelixDB is an open‑source Rust database that natively blends graph and vector storage, exposing a language‑agnostic query API for AI agents. It ships with a CLI that can spin up a local instance, scaffold projects, and even hand off to LLM‑based code generators. SDKs for Rust, TypeScript, Python and Go let you build queries as code, which are sent as JSON ASTs to the server. A managed cloud offering adds HA, auto‑scaling readers and integrated full‑text/vector search, making HelixDB suitable for RAG, agent memory, and knowledge‑graph applications.

A collection of standardized skill packages that provide AI agents with specialized knowledge and best practices for developing with Supabase and Postgres.

An ACP adapter for OpenAI Codex that allows ACP-compatible clients to interact with Codex as an agent server for AI-assisted coding and system operations.

An open-source library of 165 evidence-based pedagogical skills designed for AI agent orchestration to provide research-grounded support for educators and learners.

A remote software testing and execution control plane that allows developers and AI agents to run repository commands on managed remote runners instead of local machines.

A curated library of executable workflows and reference materials that enable AI agents to automate tasks and generate code for the Salesforce platform.

A plug-and-play Python library providing benchmarked implementations of multiple object tracking algorithms for any detection model.

An experimental fork of Windows Terminal with native AI agent integration, allowing users to to interact with ACP-compatible agents directly within their shell context.

An SLO-aware benchmarking and evaluation platform that simulates real-world workloads to optimize LLM inference performance, resource needs, and operational limits.

An MCP server that enables AI models to search DuckDuckGo and fetch webpage content with built-in bot detection bypass and context-saving URL shortening.

A self-hosted agent platform for teams that provides isolated Kubernetes sandboxes for AI agents to execute real work via Slack or API.

A proofreading skill for AI agents that removes "AI flavor" from Traditional Chinese text and localizes it for Taiwan, ensuring content feels human-written and natural.

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

A browser extension that provides centralized management for AI relay accounts, API credentials, and self-hosted gateways, featuring automated check-ins and price comparisons.

A resilient public-page reader for Claude Code that bypasses bot detection and WAFs to retrieve public web content without API keys.

A macOS menu bar application that provides centralized, real-time monitoring of usage quotas for multiple AI coding assistants.

An open-source ETL platform that compiles visual pipelines to SQL and runs them on DuckDB, allowing teams to deploy and own their data infrastructure without per-row billing.