Davin Hills

goauto. Go package for building automation tools

golevel7. Go Level 7 is a decoder / encoder for HL7

gofhir. A Healthcare FHIR client for Go

wiggle. Multi-Node LLM Processing Framework

EmbeddixDB. EmbeddixDB is a high-performance vector database written in Go, designed for LLM memory use cases

termai. Terminal ai integrates with most AI APIs

second-opinion. LLM-driven code review MCP server for Git repos with pluggable model support.

yaggg. Yet Another Go Generic Generator

mcp-pr. MCP server for AI-powered code review using Claude, GPT, or Gemini. Review staged/unstaged git changes, specific commits, or arbitrary code snippets. Returns structured findings with severity, suggestions, and line numbers. Integrates with Claude Desktop and MCP-compatible clients.

langgraph-go. Go-native orchestration framework for building stateful, graph-based LLM and tool workflows. Model reasoning pipelines as directed graphs with typed state, deterministic replay, checkpointing, and built-in observability. Supports OpenAI, Anthropic, Google, and AWS Bedrock adapters.

alas. ALaS (Artificial Language for Autonomous Systems) - A programming language designed for machine generation and manipulation by AI/LLM systems. Uses JSON as its primary representation format, optimized for programmatic generation rather than human readability. Includes interpreter and LLVM backend for native compilation.

specBuilder. A requirements compiler that transforms product ideas into formal, machine-usable specifications for AI coding agents. Uses LLMs as constrained compilers with strict structured outputs—not chatbots. Generates complete project specs with traceability, schema validation, and exportable AI Coder Packs

prism. Local-first AI code review CLI. Reviews git diffs, commits, ranges, and PRs using Anthropic, OpenAI, Gemini, or Ollama. Outputs text, JSON, SARIF, and Markdown. Pre-commit hooks, caching, multi-model compare mode, and CI-friendly exit codes.

goalchemy. Go SDK for the IBM Alchemy API

plancritic. CLI tool that reviews software implementation plans and returns structured critique: contradictions, ambiguities, missing prerequisites, and suggested patches.

ai-manager. ai-manager gives access to multiple modern LLMs

QuantaDB. QuantaDB is a complete SQL database featuring persistent storage, MVCC transactions, crash recovery, and enterprise-grade query processing capabilities.

goflow. Visual workflow orchestration system for Model Context Protocol (MCP) servers. Chain multiple MCP tools into sophisticated workflows with conditional logic, data transformation, and parallel execution. Built-in TUI editor, programmatic API, and robust error handling. Pure Go, domain-driven design.

golevel7v2. Go library for parsing, encoding, and manipulating HL7 v2.x healthcare messages. Features streaming parser with MLLP support, struct marshaling/unmarshaling via tags, rule-based validation, ACK/NAK generation, and network client/server for HL7 transport.

visDB. Database visualization tool that connects to PostgreSQL, MySQL, SQLite, SQL Server, and MongoDB to generate interactive ERD diagrams. Features automatic schema introspection, multiple layout algorithms, drag-and-drop positioning, minimap navigation, light/dark themes, undo/redo history, and export to SVG/PNG/PDF. Includes CLI for headless use.

layered. Layer Editor is a text editor

craftMCP. An MCP client / Host

RelatixDB. High-performance, local graph database intended for use as a Model Context Protocol (MCP) tool

swarm. An AI based, scriptable logic system

goredux. A Redux implementation in Go

goterm. A powerful, feature-rich Go library for building terminal user interfaces with comprehensive color support, text styling, and screen buffer management.

lg-vis. Visual Editor for langgraph-go

keystorm. KeyStorm is a programming editor in the spirit of vim written in Go

speccritic. CLI tool that evaluates software specifications as formal contracts, identifying defects before implementation begins

clarion. Evidence-backed documentation generation for Go repositories. Scans code, builds a Fact Model, generates architecture/API/data-model/runbook docs via LLM — every claim traceable to source.