Explore the directory

An automated Unity 6 game-development pipeline powered by Claude Code that turns a one-sentence game idea into a full Unity project with architecture, code and tests.

• Coding agents

An MCP server that lets an AI assistant drive Frida for Android dynamic analysis and reverse engineering, automating instrumentation on a rooted device.

• MCP servers
• Security

Microsoft's on-device AI inference solution for running generative AI models locally through a CLI, SDK or REST API; this repository holds tutorials and examples for it.

• Inference

A local tool that compiles coding-agent sessions, folders and repositories into self-describing SQLite cells an agent can query by SQL, keyword or meaning through MCP.

• Agent memory
• RAG

An in-browser vector store built as a Rust-to-WebAssembly HNSW engine that persists to the browser's private file system and stays consistent across tabs.

• Databases

A TypeScript agent framework built around single-purpose AI personalities instead of one general-purpose assistant, with five ready-made specialist agents.

• Agent frameworks

The official implementation of a CIKM 2024 paper that improves multimodal electronic health record prediction with retrieval-augmented summaries from a knowledge graph.

• RAG
• Papers

A research framework for fine-tuning and evaluating ECG-language models, which combine electrocardiogram signals with text for tasks such as ECG question answering.

• Models

The core Laravel package of DreamFactory, a self-hosted platform that generates governed REST API access to any data source for enterprise apps and local LLMs.

• APIs
• Backend

A Figma plugin that scores components for AI code-generation readiness, fixes common structural issues, and generates prompts that build a reusable design-system skill.

• Design tools

A companion toolkit that adds LoRA fine-tuning to CosyVoice v3 for single-speaker voice cloning on one consumer GPU, since the upstream code only supports full fine-tuning.

• Models
• Speech

A shared code-generation workflow skill for both Codex and Claude Code, built from a curated set of Chinese-language AI coding prompts.

• Agent skills

A batch-inference engine for large mixture-of-experts language models that minimizes the total time to finish a batch of requests rather than single-request latency.

• Inference

A self-healing multi-agent runtime, built in Go, that treats agents as autonomous cognitive processes rather than functions called by a central orchestrator.

• Agent frameworks

A native zero-trust overlay network for agent-to-agent communication, built on OpenZiti, giving agents the identity, discovery, policy and connectivity to interact safely.

• Security
• Networking

A CLI that keeps one editable source of agents, skills, rules, hooks and MCP configuration in Markdown and YAML, then syncs it into each AI coding tool's native files.

• Agent skills

An orchestration and organizational-memory layer for multi-agent systems, implementing the Agent Message Transfer Protocol for addressing and delivery between agents.

• Agent frameworks
• Agent memory

A FastAPI starter for an authenticated, document-scoped retrieval-augmented generation system with built-in evaluation, rather than a bare upload-and-ask demo.

• RAG

A portfolio of example agentic AI systems spanning research, software engineering, productivity and education, meant to demonstrate multi-agent collaboration and tool use.

• Tutorials

A BloodHound-style risk-analysis tool for multi-agent AI architectures that finds reachable attack paths from untrusted input to sensitive data or external actions.

• Security

An unofficial Mandarin Chinese fine-tune of the Supertonic-3 on-device text-to-speech model, distributed as optimized ONNX graphs with streaming synthesis and Chinese-specific text normalization for dates, money and phone numbers.

• Speech

A practical knowledge base and Python SDK for the OpenDataProducts.org standards family (ODPS, ODPC, ODPV and ODPG), with FAQs, reusable YAML examples, and SDK guides for validating, generating and automating data product specifications.

• Data engineering
• Documentation tools

An engineering log and Python test scripts that verify Apple Neural Engine primitives such as gemm, softmax, attention and transformer blocks on Linux, comparing ANE output against NumPy on real M1 and M1 Max Asahi Linux hardware.

• Inference

An LLM inference compiler and runtime that compiles a Hugging Face checkpoint into a static packet stream and executes it with a persistent, resident GPU interpreter, avoiding per-operation CPU dispatch, with an OpenAI-compatible HTTP server.

• Inference