Explore the directory

An MCP server that connects AI assistants to the Unity Editor and Unity Hub, exposing more than 330 tools for scene management, GameObjects, builds, shaders, terrain, physics, and multiplayer testing so an assistant can build and control a Unity project directly.

• MCP servers

A Go reimplementation of the pi command-line coding agent, supporting headless scripted execution and an interactive REPL, with tools for reading, writing, and running code across multiple LLM providers.

• Coding agents

A personal, gradually published knowledge base of advanced DevOps, Linux, cloud, big-data and security tips, tricks, debugging notes and fixes, accumulated over 20 years of consulting work.

• Books
• Curated lists

A hands-on tutorial that builds a ChatGPT-style language model in PyTorch step by step, covering tokenization, embeddings, attention, and the transformer block through interactive notebooks.

• Tutorials

A Go library and CLI that automatically detects and fixes malformed JSON output from large language models, such as unclosed brackets, mixed quotes, or trailing commas.

• CLI tools
• Libraries

A local-first voice AI runtime providing transcription, speaker diarization, text-to-speech, and voice cloning through a desktop app, web UI, CLI, and an OpenAI-compatible local API.

• Speech

A workspace multiplexer for AI coding agents that runs Claude Code, Codex, Gemini, or other CLI agents in parallel git worktrees on Windows and macOS, with a daemon that survives reboots and an iPhone app for approving agent questions remotely.

• Coding agents

A living guide to making an OpenClaw AI agent faster, cheaper, and more reliable in production, covering cost visibility, provider failover, fast mode, prompt-cache retention, and memory and context management.

• Books

An MCP server that exposes every Dokploy API endpoint as a tool, letting AI assistants manage projects, applications, databases, backups, and other Dokploy resources through natural language.

• MCP servers
• Hosting

This project provides scripts and documentation for running multi-node inference of Qwen3.8-Flash-Next in NVFP4 across two NVIDIA DGX Spark nodes using vLLM with tensor parallelism, expert parallelism and multi-token prediction.

• Inference

A collection of example projects for self-hosting Stable Diffusion family models as HTTP services with BentoML, covering image and video generation from text prompts.

• Generative media
• Tutorials

A lightweight governance framework that wraps an LLM client or agent loop with context management, tool governance, risk classification, and observability so agents move from demo-ready to production-reliable.

• Agent frameworks
• Security

An open-source, 3D-printable desktop robot that physically acts out what an AI coding agent is doing, reading, thinking, coding, and finishing tasks, driven over Wi-Fi by hooks from Cursor, Claude Code, or Antigravity CLI.

• Coding agents

A cross-platform command-line tool that measures the real tokens-per-second throughput of local LLMs running through Ollama.

• AI evals

A production-tested SRE agent platform where a preconfigured team of specialist agents investigates infrastructure incidents by correlating traces, logs, and metrics, then recommends fixes inside operator-defined guardrails.

• Agent frameworks
• Monitoring

A benchmarking framework for evaluating the foundational components of retrieval-augmented generation systems, comparing text splitters, retrievers, and orchestrators against multiple evaluation metrics.

• RAG
• AI evals

A tool that converts a developer's Claude Code, Codex CLI, Copilot, Cursor, and Gemini CLI session transcripts into a searchable, interlinked local knowledge base, following Andrej Karpathy's LLM Wiki pattern.

• Coding agents
• AI evals

A GitHub Action and CLI tool that runs automated code reviews using DeepSeek models, commenting directly on pull requests or reviewing local git diffs from the command line.

• Code quality
• CI/CD

A Docker-based tool, now deprecated in favor of Docker Desktop's MCP Toolkit, that ran agentic workflows written in Markdown prompt files against dockerized tools and any LLM.

• Agent frameworks
• Containers

A library that wraps a trained scikit-learn or XGBoost model as an LLM-callable tool, generating a JSON schema and validated types automatically so agent frameworks can call it directly.

• Libraries

An MCP server that queries China's official 12306 railway system for ticket availability, fares, station information, stops, and transfer routes, for use by AI assistants and automation scripts.

• MCP servers

An open-source platform that assigns a dedicated autonomous AI agent to each task, such as a feature, report, campaign, or audit, and runs many of them in parallel with a shared task tracker and dashboard.

• Agent frameworks
• Workflow automation

A personal AI assistant that runs across a user's own Macs, handling voice, vision, screen, meetings, and calls in real time, and rewriting its own code overnight based on learned patterns.

• Agent frameworks

An open-source, self-hosted AI agent runtime built on .NET that runs as a desktop app or embeds into a .NET application, extensible with plugins and controllable remotely from a CLI, IDEs, or chat bots.

• Agent frameworks