Doctrine is a system of standing rules that govern how code is built across all agents and sessions. It encompasses house style, naming conventions, commit formats, and tests, enforced through git hooks and review processes. Doctrine layers a standard foundation from Pullboard with repository-specific customizations that persist across sessions.
GitSwarm is a decentralized system for collaborative AI inference where identical workers autonomously contribute to a shared Git repository as the collective memory. Workers choose their own tasks based on repository state, with no central planner or assigned roles, and the system uses semantic inheritance to allow building on work across branches without merging.
A developer created a system to identify rare Git commit hashes based on aesthetic patterns like palindromes, repeated characters, and ascending sequences. The methodology uses pattern matching against the 16^7 possible hexadecimal hashes, with scoring computed in-browser and visualization rendered via GPU shader.
Memdebug is a local tool that monitors AI agent memory stored in folders, git repositories, or platforms like Open WebUI and Mem0. It records memory changes in a tamper-evident ledger, detects unauthorized edits, and allows safe rollback of markdown memory without blocking attacks in real-time.
Pullboard is a git-based agent development workflow that coordinates multiple AI agents building software from human-approved specifications. Agents work in separate lanes with built-in verification, spec-driven requirements, and enforced rules (Doctrine), ensuring coherent development where humans retain final decision authority.
A software development methodology combines AI-assisted coding with spec-driven development, treating business requirements as the single source of truth rather than generated code. All specifications—requirements, diagrams, and use cases—are versioned in Git and reviewed by stakeholders, enabling AI to automatically maintain consistency across downstream artifacts while improving traceability and maintainability.
TaskHandoff is a self-hosted control plane for managing and collaborating with containerized AI agents across local and remote machines. It provides multi-node management, isolated workspaces, AI session control, Git integration, and chat platform connectivity through a unified interface available on desktop, mobile, and web.
guardrails-md is an open-source tool that intercepts commands from coding agents and scores them against a GUARDRAILS.md file using a decision model, blocking destructive, credential-exposing, or policy-violating commands within ~100ms. The system uses fixed scoring questions rather than full LLM generations, fails closed by default, and requires human approval via pull requests to change policies.