Explore the directory

An AI-enhanced terminal development environment: a coding agent supporting Claude, GPT, Grok, DeepSeek, Gemini and 300+ other models, usable interactively, as a one-shot CLI, or as a ZSH plugin.

• Coding agents

A Chinese-language curated collection of Model Context Protocol resources, covering what MCP is, its clients, and a categorized list of MCP servers across dozens of domains.

• Curated lists

A CLI and library that converts a codebase into a single LLM prompt, with prompt templating, token counting, and a matching Python SDK and MCP server.

• MCP servers
• CLI tools

A fast, flexible LLM inference engine in Rust, with an agentic runtime, OpenAI- and Anthropic-compatible serving, and Rust and Python SDKs.

• Inference

An Obsidian plugin that runs coding agents such as opencode, Claude Code and Codex inside a user's vault for research, writing and knowledge work.

• Coding agents

A lightweight, open-source framework for orchestrating multiple specialized AI agents and routing conversations between them, in Python, TypeScript and now on-device Swift.

• Agent frameworks

A sample application demonstrating a ChatGPT-style, Retrieval-Augmented Generation experience over a company's own documents, using Azure OpenAI and Azure AI Search.

• RAG

An agent-powered vulnerability scanner that runs in a developer's own infrastructure, using top AI models at maximum thinking effort to find hard-to-spot security issues in large codebases.

• Security

An MCP server that lets agents and LLMs automate native iOS and Android apps on simulators, emulators or real devices through one platform-agnostic interface.

• MCP servers
• Testing

A Python library for topic modeling that combines BERT-style embeddings with class-based TF-IDF to produce dense, easily interpreted topic clusters.

• Libraries

A PyTorch implementation of Reinforcement Learning with Human Feedback (RLHF) on top of the PaLM architecture, aimed at replicating a ChatGPT-style training pipeline in the open.

• Models

A repository of 22 hands-on Jupyter Notebook tutorials on prompt engineering, from basic templates through chain-of-thought, self-consistency and tree-of-thought prompting.

• Tutorials

A native Android chat client that lets a user switch between multiple LLM providers, with Material You design, a workspace agent environment and MCP support.

• Inference
• Mobile

An audio-processing library built on Apple's MLX framework for fast text-to-speech, speech-to-text, speech-to-speech and music generation on Apple Silicon.

• Speech

A Python framework for building autonomous AI agents, with prebuilt ready-to-run agents, MCP tool integration, and a layered OCR pipeline for document processing.

• Agent frameworks

An open-source, local-first desktop app that turns a prompt into a prototype, slide deck or marketing asset using whichever AI model a developer already has access to.

• Design tools

Source control for coding agents: it links every commit back to the session, prompts and tool calls that produced it, so multiple agents can share memory in one codebase.

• Coding agents
• Git

A native macOS AI harness that keeps agents, memory, tools and identity on a user's own Mac, running fully offline in Swift with no Electron.

• Agent frameworks
• Agent memory

A roughly 100-line AI software engineering agent that solves GitHub issues or assists on the command line, scoring above 74% on SWE-bench verified with no tool-calling interface.

• Coding agents

A metaprogramming code generator for Swift, built on SwiftSyntax, that removes boilerplate by generating code such as mocks, equality and Codable conformances from templates.

• Code quality

A self-hosted platform that keeps a user's AI agents and workspaces available across desktop, mobile, browser and API, tracking tasks on a shared board.

• Agent frameworks

An offline, self-hosted enterprise knowledge substrate that builds a bitemporal knowledge graph with ontology and conflict detection, so agents can reason over how understanding changed over time.

• Agent memory

A free, local multi-agent harness that turns terminal coding-agent CLIs you already run, such as Claude Code and Codex, into a coordinated office of agents visualized on a shared 2D floor.

• Coding agents

A modular plugin ecosystem and marketplace for the DeepSeek Harness (DSH) web GUI, adding a task board, remote control, SSH terminal, Git visualization and themes.

• Coding agents