Explore the directory

An extension that ports OpenCode-style Model Context Protocol client support to the Pi coding agent, letting it connect to local or remote MCP servers using the same configuration format OpenCode uses.

• MCP servers

An AI-agent-first work orchestration framework that lets developers define typed operations, compose them into DAG pipelines, and execute each step with any AI agent or script executor.

• Agent frameworks
• Workflow automation

An open-source, locally-runnable AI UI design tool that turns a description, screenshot or wireframe sketch into interactive frontend code on an infinite canvas, using local models through Ollama.

• Design tools

A sample personal-shopping chatbot in Java that routes customer requests to separate product, sales and refund agents, using Spring AI, Azure OpenAI and Azure Cosmos DB for both transactional data and vector search.

• Agent frameworks
• Tutorials

A Rust command-line tool that infers a typed schema from a directory of Markdown files, validates their frontmatter against it, and adds local hybrid vector and keyword search over the whole corpus.

• RAG
• Documentation tools

A CLI-first tool for running and serving automatic speech recognition models locally, with a Ryzen AI NPU backend as well as CPU and GPU, for developers integrating local speech recognition into their own apps.

• Speech

A collection of curated AI agent skills for coding assistants, paired with a local semantic search engine over those skills powered by the Gemma embedding model, with no API keys or cloud dependency.

• Agent skills
• Agent memory

An open-source AI agent platform and LLM gateway that unifies more than 170 models through MCP and LangGraph orchestration, with row-level multi-tenant security, a RAG knowledge base and an agent marketplace.

• Agent frameworks
• LLM gateways

A generative-AI-powered application framework for large-scale data management and AI model serving, connecting compute services across distributed locations through virtual workspaces and remote procedure calls.

• Inference
• Backend

A retrieval-augmented generation system that represents facts involving more than two entities as hyperedges in a hypergraph, using a memory-guided beam retriever and a trained retriever to reason over them.

• RAG

A desktop coding agent for Mac and Windows that can be sent tasks by text or voice from a phone, works unattended for hours, and has a second AI agent review every finished job before you see it.

• Coding agents

A peer-to-peer network of ordinary machines that runs large language models across the network so a prompt is served without a central operator, encrypted so it never leaves the sender's device in clear text.

• Inference

A demonstration project showing how a high-level Cursor agent can delegate a trip-planning task to specialized flight- and hotel-research subagents using Cursor's agent skills.

• Agent frameworks
• Tutorials

A zero-dependency local proxy that lets the Codex CLI call DeepSeek, MiMo or other chat-completion models by translating between OpenAI's Responses API and the Chat Completions API, with a desktop UI for managing providers and keys.

• LLM gateways

A private AI assistant operating system for an NVIDIA Jetson appliance, running local models by default with cloud AI as an explicit opt-in, and controlling the whole device through MCP tools.

• Agent frameworks

A hands-on lab series of Jupyter notebooks and Bicep templates that walk through Microsoft Foundry, Azure's unified platform for provisioning, orchestrating and governing AI agents, models and tools.

• Agent frameworks
• Tutorials

A governed, local-first system for training small language models that measures each new model against a benchmark, promotes only improvements through a regression-aware gate, and archives the evidence for every decision.

• Models
• AI evals

A free, hands-on curriculum that takes a Python developer from foundations through prompt engineering, LLM APIs, RAG, agents, fine-tuning and MLOps to production AI systems, with notebooks and real projects.

• Tutorials

A code generator and SDK, distributed as NuGet packages, that make it easier to build features that call into and out of a VBS (virtualization-based security) enclave on Windows, for C++ and Rust host applications.

• Libraries

A command-line code generator that turns a Cantera combustion mechanism file into Python, C++ or Fortran source implementing that mechanism's thermochemistry.

• CLI tools

A coding-agent plugin that turns a named research paper into a local, interactive site where every claim links back to the exact page and quote it comes from, distinguishing measured results from the authors' own interpretation.

• Agent skills
• RAG

A collection of production-ready Python examples for the CUBRID database, with five-minute quickstarts for FastAPI and SQLAlchemy, a Java-to-Python migration guide, copy-and-customize service templates, and benchmark-backed performance patterns.

• Databases
• Tutorials

A statically-typed language, compiling to native binaries via Rust and to WebAssembly with byte-identical output, designed around one metric: how often code still compiles and passes its tests after a series of AI-driven edits.

• Languages

A native Android client for the OpenCode AI coding agent that connects to a running OpenCode server, giving real-time AI chat, a terminal, a file browser and a code editor from a phone or tablet.

• Coding agents