Explore the directory

An open-source AI coding agent that works from the terminal, an IDE, a desktop app, a browser or chat, with built-in memory, skills, subagents and MCP support.

• Coding agents

A Claude Code plugin that adds a status line showing context window usage, active tools, running subagents and todo progress.

• Agent skills

A kanban-based tool for planning and reviewing work carried out by coding agents such as Claude Code, Codex and Gemini CLI, with per-task workspaces and diff review.

• Coding agents

An open-source platform for building internal AI agents, apps and workflow automations that connect to databases, AI models and business systems, self-hosted or in Budibase Cloud.

• Backend
• Workflow automation

A terminal-based AI coding agent that wires your tools, code and workflows into a large language model of your choice, with support for switching models mid-session.

• Coding agents
• Terminals

A TypeScript framework for building AI-powered applications and agents, with model routing across many providers, a graph-based workflow engine, memory and built-in evaluation.

• Agent frameworks

A command-line tool that packs an entire code repository into a single AI-friendly file, for feeding a codebase to large language models such as Claude, ChatGPT, Gemini or DeepSeek.

• CLI tools

A four-volume textbook and curriculum from Harvard's CS249r course on engineering machine learning systems, paired with hands-on labs, a from-scratch framework, hardware kits and a simulator.

• Tutorials
• Books

An array framework for machine learning on Apple silicon, with a NumPy-like Python API and matching C++, C and Swift APIs, plus higher-level packages that follow PyTorch.

• Models

A model-agnostic SDK for building, orchestrating and deploying AI agents and multi-agent systems, with support for Python, .NET and Java.

• Agent frameworks

An open-source, privacy-first web analytics tool that avoids cookies and personal data, available self-hosted or as a managed cloud service.

• Monitoring

Persistent memory for AI coding agents such as Claude Code, Cursor, Codex and Gemini CLI, so an agent keeps a project's context across sessions instead of being re-briefed each time.

• Agent memory

An open-source Windows and macOS desktop client for DeepSeek Harness that wraps its local web UI, host service and plugin system in a native app, with a built-in plugin marketplace.

• Agent frameworks

A design skill for AI coding agents such as Claude Code, Cursor and Codex that builds web page UI while avoiding common AI-generated design defaults, using a set of automated checks.

• Agent skills
• Design tools

A JavaScript library that adds an in-page AI agent to any website, so a user can control web interfaces such as forms and multi-step workflows with natural language.

• Agent frameworks
• Libraries

The official code repository for the O'Reilly book Hands-On Large Language Models, with runnable notebooks for every chapter's examples.

• Books

An open-source PDF parser that extracts Markdown, JSON with bounding boxes, and HTML from PDFs for AI and RAG pipelines, and automates PDF accessibility tagging.

• RAG

An open-source vector database and search infrastructure for AI applications, with a small core API and an optional hosted cloud service.

• Databases

An MCP server and matching Blender add-on that connect Blender to any large language model for prompt-assisted 3D modeling, scene creation and manipulation.

• MCP servers
• Design tools

A command-line tool that scans git repositories, files and piped input for secrets such as passwords, API keys and tokens.

• Security

A curated hub of generative AI research updates, courses, interview preparation material and notebooks, organized by whether the reader wants to use, build or understand AI systems.

• Tutorials
• Curated lists

A community-maintained collection of more than 42 runnable notebooks, each demonstrating a specific technique for building retrieval-augmented generation systems, from foundational to advanced.

• RAG
• Tutorials

An autonomous research agent that searches the web and local documents to produce detailed, cited reports on a given topic, using planner and execution agents with any LLM provider.

• Agent frameworks
• RAG

A tool that turns websites and logged-in browser sessions into command-line interfaces, so an AI agent can navigate, fill forms and extract data through the user's own browser.

• CLI tools
• Browser automation