AI-Driven Scientific and Algorithmic Discovery

A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

A Claude or Codex skill for deliberate skill development during AI-assisted coding

Build PowerPoint presentations with JavaScript. Works with Node, React, web browsers, and more.

Personal memory you own, in files you can actually read

The visual editor for React.

visual editor (figma) for your react apps, edit UI elements live and directly changes source files. no API key, no AI..

The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI

runs anywhere. uses anything

Realistic examples of building evals and optimizing agents with Harbor

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Research infra for creating RL environments, post-training, and evals

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

OCR model that handles complex tables, forms, handwriting with full layout.

Your One-Stop Publication Workbench

Show usage stats for OpenAI Codex and Claude Code, without having to login.

AI agents running research on single-GPU nanochat training automatically

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

Web AI chat client implementing unlinkable inference

Framework for evaluating and improving agents

Service for sharing data resource between asta users, clients, and agents

Give your agents the power of the Hugging Face ecosystem

A tool to use the Ai2 Open Coding Agents Soft-Verified Efficient Repository Agents (SERA) model with Claude Code

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

The open agent skills tool - npx skills