Explore the directory

A structured, visual guide to Claude Code that teaches its features with diagrams and copy-paste templates, organized as a guided learning path with self-assessment quizzes.

• Tutorials

An opinionated Python code formatter that reformats files in place with minimal configuration, producing consistent formatting across projects.

• Code quality

A desktop, mobile and web client for chatting with ChatGPT, Claude, Gemini and other large language models, including local models run through Ollama, from one interface.

• Inference

An AI-powered code review CLI that reads git diffs and sends changed files to a large language model agent with tool access, producing line-level review comments while combining deterministic checks with agent reasoning.

• Code quality

A low-level orchestration framework for building long-running, stateful agents, with durable execution that resumes after failures, human-in-the-loop control, and short- and long-term memory.

• Agent frameworks

A framework and runtime for building agent platforms: an SDK to build agents, a runtime to serve them as a service, and a web UI to manage and observe them.

• Agent frameworks

An agent skill that produces editorial-style architecture, flowchart, and other diagrams as self-contained HTML and SVG, matched to a project's own visual style.

• Agent skills
• Design tools

A deep learning optimization library for distributed training and inference of large models, providing memory- and compute-efficient parallelism techniques such as ZeRO and 3D parallelism.

• Models
• Inference

agent-browser is a fast, native Rust CLI for driving a real Chrome browser from an AI agent, using accessibility-tree snapshots and stable element references instead of fragile CSS selectors.

• Browser automation

A self-hostable, open-source cloud operating system that gives developers cloud storage, a database, serverless workers and AI access for building and publishing web apps.

• Backend
• Hosting

Ray is a unified Python framework for scaling AI and general compute workloads from a laptop to a cluster, pairing a distributed runtime core with a set of AI libraries.

• Models
• Data engineering

A self-hosted, open-source implementation of the Tailscale control server for running a private WireGuard-based network without Tailscale's own hosted service.

• Networking

Kong Gateway is a cloud-native, platform-agnostic API gateway that also governs LLM and MCP traffic, adding multi-provider AI routing, semantic security and MCP traffic analytics on top of its core proxying and plugin system.

• LLM gateways
• APIs

Jan is an open-source, offline-capable alternative to ChatGPT that downloads and runs LLMs locally, keeping full control over data and model choice.

• Inference

LibreChat is a self-hostable, enhanced ChatGPT-style web client that connects to many model providers and adds agents, MCP tools, custom skills, sandboxed code execution and a shared agent marketplace.

• Inference

codebase-memory-mcp is a native MCP server that indexes a codebase into a persistent knowledge graph in milliseconds, giving a coding agent structural queries instead of repeated grep and file-read cycles.

• MCP servers
• Agent memory

Milvus is a high-performance, cloud-native vector database built to store and search billions of vectors representing unstructured data such as text, images and other multi-modal information.

• Databases

Scientific Agent Skills is a library of 166 validated Agent Skills, plus more than a hundred scientific databases, giving any compatible AI agent curated workflows for biology, chemistry, medicine and drug discovery.

• Agent skills

AAS Core is a local control plane and catalog of more than 2,400 installable SKILL.md playbooks that lets Codex or Claude search, inspect and select skills for a project, then preview a plan before anything actually changes.

• Agent skills
• Curated lists

CowAgent is an open-source, self-hosted "agent harness" that plans tasks, runs tools and skills, and improves itself over time through memory and a growing personal knowledge base, reachable across the web and major chat platforms.

• Agent frameworks

A tool that indexes a codebase into a knowledge graph of dependencies, call chains and execution flow, then exposes it to AI coding agents through MCP.

• Agent memory

exo connects a user's own devices into a single AI cluster, letting a model larger than any one device's memory run by splitting it across machines, with day-0 RDMA-over-Thunderbolt support for lower latency.

• Inference

TextGen is a desktop application for running local LLMs with text, vision and tool-calling support, offering a chat UI plus an OpenAI and Anthropic-compatible API entirely offline.

• Inference

JeecgBoot is an enterprise low-code development platform that generates a full front-end and back-end system from a natural-language description, alongside a built-in AI chat, knowledge-base and workflow-orchestration suite.

• Web frameworks