An open-source, token-efficient AI agent that reduces costs through high cache hit rates and a minimal toolset, supporting any OpenAI-compatible model for coding and general tasks.

An evidence-driven framework for creating and maintaining AI agent skills that uses behavioral testing to ensure every skill demonstrably improves performance.

An open-source infrastructure layer for building and operating persistent, coordinated, multi-agent systems at organizational scale.

A modular suite of AI agent skills for self-media content production, covering everything from trend research and strategy to platform-native copywriting and publishing.

A collection of modular agent skills for Claude Code and Codex that provide journalists and researchers with specialized workflows for source verification, records requests, and professional reporting.

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 local-first agent operating system that integrates agents, visual workflows, and long-term goals to make AI work durable, repeatable, and improvable.

A framework for building AI personality profiles using structured markdown files, allowing agents to embody a user's specific voice and worldview without fine-tuning.

An AI-powered penetration testing assistant that automates security assessments using agentic workflows and isolated cloud execution.

An open-source, cross-platform AI client that allows users to self-host their AI interface and connect to local or frontier model providers to avoid vendor lock-in.

An AI-powered autonomous web browsing framework for TypeScript that allows agents to navigate, interact with, and extract data from any website using natural language commands.

An autonomous web application penetration testing agent that uses feedback-driven iteration and custom payload generation to find and exploit vulnerabilities.

dtaidistance is a Python library (with optional C acceleration) that provides fast implementations of Dynamic Time Warping and related time‑series distance measures, plus utilities for clustering, subsequence search, and visualisation.

A Java-based natural language processing framework that provides a suite of tools for analyzing raw text to extract linguistic structures and entities.

A self-hosted RSS reader and personal knowledge management tool that uses intelligent aggregation and vector databases to help users manage high-volume reading.

A local-first framework for architecture firms to build and govern AI-assisted workflows, providing persistent project memory and specialized AEC tools for Codex and Claude Code.

Model2Vec is an open‑source Python library that distills any sentence‑transformer into a tiny, static‑embedding model (8‑30 MB) that runs up to 500× faster on CPU. It offers zero‑data distillation, optional fine‑tuning for classification, and integrates with Hugging Face, Sentence‑Transformers, and LangChain. Install with `pip install model2vec`, load pre‑built models via `StaticModel.from_pretrained`, or distill your own in ~30 seconds on a CPU.

A collection of standardized AI agent skills that provide specialized instructions and resources to help AI coding agents perform Kotlin-specific development tasks.

A secure, self-hosted code agent CLI that reads and edits files and runs shell commands using OpenAI-compatible endpoints with a focus on safety and session durability.

A desktop application that runs AI browser agents using a fresh Chromium instance with ported cookies to maintain user sessions.

Vendor‑neutral Claude Fable 5 system prompt adapted for use across multiple frontier LLMs.

A multi-agent investment research system that dynamically coordinates specialist agents to build a persistent, evidence-based knowledge base for financial analysis.

A Claude Code skill that turns the AI into a Home Assistant expert for safe configuration management, modern automation development, and tablet-optimized dashboard design.

An AI agent platform that automates the connection, migration, and implementation of enterprise systems, reducing manual engineering and data mapping work.

A browser extension that uses AI to filter unwanted posts from Twitter/X feeds based on natural language descriptions of topics to avoid.

An AI-powered tool that transforms plain English descriptions into verified, structured datasets from the live web with automatic refresh schedules.

A command-line tool that syncs X bookmarks to a local knowledge base, enabling LLM-powered classification and providing AI agents with grounded local context.

An AI agent that autonomously scrapes and analyzes LinkedIn profiles to extract structured insights like pain points, values, and expertise for sales, recruiting, and investing.

A mobile and desktop interface for AI coding agents like Codex and Claude, allowing users to to manage projects and git workflows from their own local machines via a bridge server.

A collection of AI-generated command-line interfaces for websites without public APIs, enabling terminal-based interaction with platforms like rental sites and travel booking.

ChatterBot is a Python library that builds conversational bots by storing user‑bot statement pairs and later retrieving the most similar past exchange. It includes ready‑made corpora for many languages, a simple training API, and a permissive BSD‑3 license.

An MCP server that enables AI chatbots to search, explore, and analyze French national open data from data.gouv.fr through natural language conversations.

An ultra-lightweight, open-source agentic framework for building self-learning agents and deterministic multi-step workflows with persistent memory and tool integration.

An Obsidian plugin that turns your vault into an MCP server, allowing AI assistants to read, write, and navigate your notes as a connected knowledge graph.

An MCP server that integrates Home Assistant with LLMs, allowing AI assistants to control devices, manage dashboards, and troubleshoot automations via natural language.

An AI-powered personal knowledge assistance system that uses a multi-agent team to organize your life and data in a local, LLM-agnostic markdown folder structure.

An MCP server that enables AI assistants to format and publish Markdown articles directly to WeChat Official Accounts draft boxes.

A framework for continuous AI agent autonomy that wraps the AI SDK in an outer loop to iteratively verify and complete complex tasks.

A collection of tools and prompts for gptel that turns Emacs into an autonomous AI agent capable of web search, file manipulation, and system execution.

An open-source, local-first AI paper workspace that integrates PDF reading, translation, structured overviews, and rich note-taking for researchers.

An autonomous product engine that researches markets, generates feature ideas, and automatically implements them as GitHub pull requests.

An AI-powered personal knowledge management system that uses natural language to automatically organize and retrieve information within a structured Obsidian vault.

Adaptive Classifier is a PyTorch‑based library for dynamic text classification. It supports continuous learning, runtime addition of new classes, and a strategic (adversarial‑robust) mode. Built on HuggingFace transformers, it offers hybrid prototype‑+‑neural predictions, automatic ONNX export for 2‑4× faster CPU inference, and multi‑label support with adaptive thresholds. The package can be installed via `pip install adaptive-classifier`, saved/loaded locally or to the HuggingFace Hub, and includes benchmarks showing improved robustness and cost savings.

An open-source alternative to Claude Artifacts that uses Llama 3.1 to generate and instantly preview small applications from a single prompt.

A Rust implementation of the LangChain framework for building composable LLM applications with support for various models, vector stores, and agents.

An MCP server that allows AI agents to retrieve transcripts and metadata from YouTube videos, featuring pagination to handle long videos.

An AI-powered research tool that automates the gathering of information from the web and local files to generate comprehensive, in-depth reports.

A desktop application for managing, chatting with, and operating AI agents and their skills via a centralized interface.