D

developer-tools

Specification graph manager for AI-augmented projects, on the nomograph-claim substrate.

AI coding with human accountability. AI assistants can produce changes you cannot reconstruct later. agents-govern makes AI-assisted software work auditable without adding a hosted service or runtime.

Universal CLI tool isolator for Python, npm, and release binaries. Installs each tool in its own environment with clean PATH shims and optional Linux env/fs policy.

Background, auto-commit, multi-remote — invisible git sync for developer workspaces.

Hunt down Go interface implementations like a bloodhound with trust issues. Tired of grep-ing through thousands of lines trying to figure out which structs actually implement that damn interface? This tool does the heavy lifting so you don't have to suffer through another existential crisis at 3am.

git-gamble is a tool that blends TDD (Test Driven Development) + TCR (test && commit || revert) to make sure to develop the right thing 😌, baby step by baby step 👶🦶

Get Started

Configurable, review-only Agent Skill that coordinates specialized reviewers across local changes, Git refs, GitHub pull requests, and GitLab merge requests.

Zara — an empathetic AI orchestrator built on OpenCode. Multi-agent system with 8 specialists, 28+ skills, persistent memory, and adaptive personality.

MCP server and CLI for Redis/Valkey. Single binary, no runtime dependencies.

Read-only MCP server for PostgreSQL. Single binary, no runtime dependencies.

Seven evidence-first tools for bounded AI-agent decisions, resumable runs, cross-agent handoffs, verification, and reviewable releases.

A native Windows system tray app that turns GitHub and Bitbucket activity into a focused developer inbox. It monitors pull requests, reviews, comments, mentions, pushes, and other repository movement across the projects you care about, then surfaces only the items that need your attention.

My personal Claude Code skills, kept in one repo so they're available in every project.

CLI tool for simplified Git worktree management to speed up switching contexts when working collaboratively.

These projects form an open-source suite of AI infrastructure tools built for modularity, security, and self-hosted deployment, allowing users to maintain full ownership and control of their systems and data. They deliver interoperable AI functions including automation, data retrieval, encryption, and identity management that can be applied across many different industries. https://roxanneardary.com/ai-infrastructure/

Agent-shape testing harness that measures how an LLM-driven agent uses a tool's CLI, scored by an LLM judge.

Practical Git learning guide covering version control foundations, GitHub, GitLab, branching, collaboration workflows and advanced command line usage.

Shell profiles, aliases and developer environment configuration for macOS, Windows and Linux

Portable, tested Agent Skills for Git, GitLab, Jira, QA, OpenSearch, modernization, and development workflows.