Explore the directory

A collection of more than 90 tutorial projects covering large language models, retrieval-augmented generation and AI agents, organized by difficulty from beginner to advanced.

• Tutorials

A curated collection of more than 500 AI agent example projects spanning frameworks such as LangGraph, CrewAI, AutoGen and Agno, and industries from healthcare to retail, each runnable as a self-contained example.

• Tutorials

A nine-chapter interactive course that teaches how to write effective prompts for Claude, with hands-on exercises and an example playground for testing prompt changes.

• Tutorials

A framework for programming language models with compositional Python code instead of hand-written prompts, with algorithms that optimize the prompts and weights of the resulting pipeline.

• Agent frameworks

An open-source context database for AI agents that organizes knowledge, memory and skills as a browsable virtual filesystem instead of an opaque vector index.

• Agent memory

A Python library that uses large language models to pull structured information out of unstructured text, mapping every extracted value back to its exact location in the source for verification.

• RAG

An open-source multimodal AI agent stack combining Agent TARS, a general-purpose GUI and vision agent driven from a CLI or web UI, with UI-TARS Desktop, a native desktop application built on the UI-TARS model.

• Agent frameworks

A multi-agent orchestration layer for Claude Code that adds an autopilot command and configurable workflow stages so a task is planned, built and checked by coordinated agents rather than a single session.

• Coding agents
• Agent frameworks

A community-maintained collection of custom agents, instructions, skills, hooks, workflows and plugins for customizing GitHub Copilot, browsable on a companion website with search and filtering.

• Agent skills
• Curated lists

A Python library that adds retrieval-augmented generation to an application: ingest files such as PDF, text or Markdown, then ask questions over them using any supported LLM and vector store.

• RAG

A browser-based database schema editor and SQL generator for building entity-relationship diagrams, exporting SQL scripts, and generating migrations.

• Design tools
• Databases

An open-source agent workspace for research, content and software development that lets teams choose among model providers and open-source agent harnesses.

• Agent frameworks

A text-to-speech model built for dialogue scenarios such as an LLM assistant, generating multi-speaker conversational speech with control over prosody, laughter, pauses and interjections.

• Speech

A retrieval-augmented generation framework that builds a knowledge graph from documents and combines it with vector retrieval, aiming for simpler and faster indexing and querying than typical RAG pipelines.

• RAG

A marketplace of agentic building blocks, including subagents, skills and slash commands, built from one source and installable natively into Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot and other agent harnesses.

• Agent skills

Open-source communication infrastructure that sends notifications across inbox, email, SMS, push and chat channels through one API, and connects AI agents to those same channels through a unified conversation model.

• APIs
• Backend

A local-first, Rust-based agent harness with one core that runs as a desktop app, browser UI, terminal client and library, connecting to whichever LLM, memory or search engine a user already runs.

• Agent frameworks

The official inference framework for 1-bit large language models such as BitNet b1.58, with optimized kernels for fast, lossless inference on CPU and GPU.

• Inference

An open-source, cloud-native distributed SQL database with MySQL compatibility, built for high availability, horizontal and vertical scalability, and hybrid transactional and analytical workloads.

• Databases

A terminal multiplexer built as a runtime for coding agents, keeping their sessions alive in a background server across disconnects and marking every pane as working, blocked or idle.

• Coding agents
• Terminals

An open-source low-code platform for building internal tools such as admin panels, dashboards and operational apps on existing databases, APIs and SaaS systems, with AI app generation and an MCP server for coding agents.

• Backend

An open-source coding agent for the terminal, built in Rust, that reads a project, edits files, runs commands and checks its own work with a hosted or local model, and can split larger jobs across several agents.

• Coding agents

An open-source agent chatbot platform that connects large language models to messaging apps such as QQ, WeChat Work, Feishu, DingTalk, Telegram and Slack, with plugins, a web UI and a code execution sandbox.

• Agent frameworks

A deep learning training system for large AI models that combines data, pipeline, tensor and ZeRO-style parallelism so a model can be split and trained across many GPUs at lower cost.

• Models