metis

A coding agent that takes tasks from exploration through verification in the terminal and on the desktop

A coding agent that helps developers working on AI and LLM coding tasks carry exploration, memory, execution, and verification forward in a repository or directory.

더닝

An iOS app that uses AI to organize a note into a title, tasks, and deadlines.

A mobile notes app where users can jot down something they need to do, and AI extracts a title, tasks, and deadlines and alerts them to approaching due dates.

solo-skills

A public repository of AI agent skills drawn from a 1-person business's recurring task automations.

A repository sharing 26 reusable AI agent skills and some execution scripts from 49 automations created while running a 1-person business.

shadok-ai

A local agent cockpit for managing multiple Claude Code tasks with schedules and worktrees

A tool for developers who want to run Claude Code sessions in parallel in separate Git worktrees and view or answer questions and status changes in a browser or Telegram.

PDF TO MP3

An MCP service that turns PDFs sent to an AI chat into audiobooks

Users who want to listen to documents can connect PDF TO MP3 to Codex or Claude, add an API key for voice generation, and ask the chat to turn an attached PDF into an audiobook.

Titan

Say what you want. Titan hears you, sees what is on your screen, and does the work in the apps you already use.

opengoal

A tool that keeps an AI coding agent’s current goal and context in Markdown files.

People working with AI coding agents can record the current task, project context, and long-term plan in separate Markdown files so they can check the direction of the work across sessions.

Littleguys

Check AI agent status and approval requests across devices from the Mac menu bar.

A menu bar app for people using multiple AI agents, such as Claude Code and Codex, to view each agent's status and messages in one place, approve commands, and manage scheduled tasks.

lifeos

A self-hosted dashboard that brings habits, goals, focus, and finances together and connects to AI.

People whose daily management tools are scattered can manage habits, goals, tasks, focus time, and finances in one dashboard, and ask an AI assistant to record or retrieve information through MCP.

babacad

A web simulator for testing industrial robot arm movements and collision avoidance.

Robotics educators and automation developers can run robot movements on the web and recalculate trajectories to examine collisions with obstacles.

PyPI

A server for running agents within an organization and finding them through natural-language search.

After an organization's developers create and publish task-specific AI agents, users can enter a question to find and run a suitable agent and receive an answer.

karotte

An open-source framework for creating and running reinforcement learning environments for AI training.

Developers creating AI training environments can generate an environment from a base template, run tasks in an isolated execution environment, and inspect conversation logs in a dashboard.

agent.reviews

Where agents choose and review software.

An open experiment, run weekly in public: a real AI agent attempts ten everyday web errands and every transcript is published verbatim.

Refuseless

Offers open-weight models with refusal responses removed through an OpenAI-compatible API.

Refuseless provides hosted inference for models with refusal responses removed, aimed at developers and teams using them for coding and cybersecurity tasks. Its API accepts the existing OpenAI chat completions request format.

dots-room

An app that turns an unused Android tablet into a pixel room for Dots.

It lets users who may miss Dots messages while working check and reply to conversations on a tablet. It exchanges messages with a web page through a local bridge, and the character reacts to the conversation.

figma-server

A server that lets agents work with Figma files through browser control.

It connects users who want to automate Figma work with their own agents to browser controls via MCP or an HTTP API after they sign in to Chromium.

innerloop

A tool that stores activity context in encrypted form on Mac so AI can find and use what it needs.

A tool for Mac users who have to explain previous work or meetings to AI again. It stores on-screen activity locally in encrypted form, supplies context requested by AI, and applies folder-specific rules.

ego (lite)

Always free, no set up.

Free Games for Seniors

Free online games for seniors that play in your browser.

A benchmark that tests the ability to recreate a Pac-Man game from a single prompt.

A test for evaluating how well AI models and execution tools recreate a Pac-Man game as a single HTML page from one request.