Explore the directory

A console tool and library that generates XmlSerializer-compatible C# classes from XML Schema (XSD) files, with data annotations, nullable adapters, and optional Entity Framework support.

• CLI tools

A native ahead-of-time and JIT compiler for TypeScript built on LLVM and MLIR, compiling .ts files to native executables, WebAssembly, or running them directly through a built-in JIT without Node.js.

• Languages

An agentic skills framework for Godot 4 game development that gives AI coding agents structured, version-specific knowledge of GDScript, C# and engine subsystems instead of generic advice.

• Agent skills

A personal, actively updated reading list of research papers on multimodal and large language models, organized into dozens of topic sections from alignment and reasoning to hallucination and world models.

• Papers

An offline retrieval-augmented generation tool that ingests local files, GitHub repositories and websites, then answers questions over them using local Ollama models with no third party ever seeing the data.

• RAG

A memory layer for AI coding agents that learns from outcomes rather than only storing everything: a memory marked wrong stops being recalled, a newer fact replaces an older one, and used memories get reinforced.

• Agent memory

A multi-agent system that analyzes a codebase's structure, dependencies and APIs in parallel and generates a README plus AI-assistant configuration files, with a GitLab mode that opens merge requests automatically.

• Documentation tools

A simple vector database implemented in plain numpy, with no server or configuration to set up, that stores embeddings in a single portable context file.

• Databases

A cross-session memory kernel for coding agents that extracts reusable knowledge from finished sessions and injects it into new ones, either as a standalone coding agent or attached to an agent already in use.

• Agent memory

A curated collection of Agent Skills, following the open Agent Skills standard, that give AI coding assistants structured, up-to-date guidance for Azure services drawn directly from Microsoft Learn documentation.

• Agent skills

A real-time voice assistant built around a small, open-weight text-to-speech model that keeps the whole spoken conversation, including the caller's own audio, in context so replies carry natural prosody across turns.

• Speech

A Rust-powered code-intelligence command-line tool for AI coding agents, building call graphs and hybrid semantic search indexes across seven languages, and exposing the results as native MCP tools for Claude Code and Codex.

• MCP servers
• Agent memory

A collection of specialized Claude Code agent definitions for code review, implementation verification, testing and quality assessment, each packaged as a single markdown configuration file.

• Agent skills
• Code quality

A modular Python library for improving how large language models use retrieved information, by generating RAG-augmented training datasets, fine-tuning models on them with parameter-efficient methods, and measuring the result with RAG-specific metrics.

• RAG

A gamified, no-code AI agent builder that turns workflow construction into a jump-and-move game so a beginner can assemble an agent by hopping through steps instead of connecting boxes and arrows on a flowchart.

• Workflow automation

A tracker that watches for official announcements of usage-limit resets on AI coding tools such as Codex, Claude Code and Grok Bot, and notifies subscribers through GitHub releases.

• Monitoring

An open-source orchestration platform for building voice-driven conversational AI applications, connecting telephony, speech recognition, language models and speech synthesis providers over websockets.

• Speech

A TypeScript SDK, agent documentation and private server emulator for building and running bots inside a RuneScape-style game, built as a testing environment for coding-agent research rather than for the live commercial game.

• AI evals

An MCP server that lets an AI agent send messages, check message quota and read profile information for a LINE Official Account through the LINE Messaging API.

• MCP servers

A public interview-preparation repository for backend developers moving into AI agent and large-language-model application engineering, covering agents, backend systems, system design and algorithms.

• Tutorials

A native Swift inference server that serves MLX language models on Apple Silicon through a strict OpenAI-compatible API, without a Python runtime, and can stream oversized mixture-of-experts models directly from disk.

• Inference

A Rust framework for building LLM applications, combining an agent harness for tool-using loops, typed task graphs for orchestration, and streaming, composable pipelines for retrieval-augmented generation.

• Agent frameworks
• RAG

A reference retrieval-augmented generation pipeline built on NVIDIA NIM microservices, with GPU-accelerated ingestion and search, a reference UI, and an optional agentic mode for multi-hop questions.

• RAG

An MCP server that connects an LLM client such as Claude Code or Claude Desktop to a Clojure project's REPL, adding tools for parenthesis-aware evaluation and editing that handle Clojure's formatting reliably.

• MCP servers