Explore the directory

A multilingual, non-autoregressive decision engine that returns typed choice, score and yes/no judgments over text in a single forward pass, across more than 100 languages, with automatic routing to the right checkpoint.

• Models

A fast, typo-tolerant open-source search engine, positioned as an alternative to Algolia and Elasticsearch, with support for geosearch and semantic search.

• RAG
• Databases

An open-source Python framework for orchestrating LLM applications, with modular pipelines and agent workflows that give explicit control over retrieval, routing, memory and generation.

• Agent frameworks
• RAG

A marketplace of Claude Code and Cowork skills, commands and plugins that guide a product manager through discovery, strategy, execution, launch and growth using established PM frameworks.

• Agent skills

A large open-source library of Claude Code skills, plugins and agent skills covering engineering, marketing, product, compliance, research and daily productivity tasks, for Claude Code and a dozen other coding agents.

• Agent skills

An open-source toolkit that gives AI agents computers to operate: desktop automation drivers, isolated cloud desktops, local macOS VMs, specialized decision models and benchmarks for computer-use agents.

• Agent frameworks
• Containers

An AI-agent skill for Claude Code and Codex that generates single-file HTML slide decks in an editorial-magazine or Swiss-design style, with matching cover images and a low-power presentation mode.

• Agent skills
• Design tools

AI SDK is a provider-agnostic TypeScript toolkit for building AI-powered applications and agents across frameworks such as Next.js, React, Svelte and Vue, with a unified API for calling many model providers.

• Agent frameworks

A terminal-based AI coding agent from SpaceXAI that understands a codebase, edits files, runs shell commands, searches the web and manages long-running tasks, interactively or headlessly.

• Coding agents
• Terminals

A file-based planning skill for AI coding agents that keeps a task plan, findings and progress on disk so long-running work survives context clearing, crashes and compaction.

• Agent skills

A shared, team-level memory hub for AI agents that turns conversations, documents and code into reusable memory assets, shared across agents and frameworks through one proxy.

• Agent memory

A reference of named laws, theories, principles and patterns that come up when discussing software development, from Conway's Law to SOLID.

• Books

A voice-enabled autonomous AI assistant that runs entirely on local hardware, browsing the web, writing and running code, and planning multi-step tasks without a cloud dependency.

• Agent frameworks
• Speech

A tool that edits raw video footage into a finished cut through a conversation with a coding agent such as Claude Code, handling filler-word removal, color grading, subtitles and animated overlays.

• Generative media

An open source AI coding agent that works from VS Code, JetBrains or the CLI, letting a developer pick from many models and switch between them mid-task at the model provider's own price.

• Coding agents

A tool that turns project work into isolated, autonomous coding-agent runs so a team can manage the work itself rather than supervise each agent, with an experimental Elixir reference implementation.

• Coding agents

A Ghostty-based macOS terminal built for AI coding agents, with vertical tabs, notifications when an agent needs attention, an in-app browser, and SSH-aware remote workspaces.

• Coding agents
• Terminals

A distributed, graph-based issue tracker for AI coding agents, built on Dolt, that replaces markdown task lists with a dependency-aware graph agents can query and update.

• Agent memory

A file format specification for describing a product's visual identity to coding agents, combining machine-readable design tokens with human-readable design rationale.

• Agent skills
• Design tools

A now-deprecated catalog of Agent Skills, folders of instructions, scripts and resources, for use and distribution with OpenAI's Codex.

• Agent skills

A Python framework for building Model Context Protocol servers, clients and interactive apps, generating tool schemas, validation and documentation automatically from ordinary Python functions.

• MCP servers

A free, cross-platform database client and SQL workspace that connects to 40 or more databases and lets a user bring their own AI model to generate, explain, and optimize queries.

• Databases

An open-source headless browser engine written in Rust for AI agent automation and web scraping, built without Chromium and compatible with Puppeteer and Playwright.

• Browser automation

An open source platform for debugging, evaluating, monitoring and optimizing production AI applications built with agents, LLMs and machine learning models, while tracking cost and access.

• AI evals
• Monitoring