A project template that turns your repository into stable infrastructure for AI-assisted development.
attractor-guided-engineering-template is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo clone entropy-cloud/attractor-guided-engineering-templateOpen or clone the template repository.
Move the relevant AGENTS.md content into your project root.
Update project-specific commands, environment rules, and sensitive areas.
This template helps you structure your code repository so that both humans and AI agents can work together efficiently. It uses a set of durable documentation files as a 'stable attractor' that the project always returns to, preventing drift and confusion across multiple sessions and contributors.
The Attractor-Guided Engineering (AGE) Template is a lightweight project scaffold designed for AI-assisted product development. It is intended for ordinary business applications such as admin systems, portals, workflow apps, dashboards, internal tools, and CRUD-heavy domain products. The template does not include generated product code; instead, it provides a durable structure for humans and AI to share requirements, owner-doc baselines, plans, verification, and project memory without heavyweight process overhead. AGE starts from the question: 'What should this repository keep converging toward as humans and AI change it over time?' The answer is a small set of durable owner files in the docs/ directory: context, backlog, requirements, design, and architecture. These files form the attractor that the project should keep returning to during fast AI-assisted iteration. Plans, tests, audits, logs, and bug notes are engineering harnesses that help prove a change moved the repo toward the attractor. AGE is not spec-driven development, nor is it a skill library. It emphasizes routing reusable skills through project-specific documentation rather than relying on a large library of skills without context. The template includes an AGENTS.md file for AI agent configuration.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 4 days ago.
18 GitHub stars indicate community interest.
0 open issues signal maintenance load.
MIT license detected.
Structuring a new business application project for AI-assisted development
Onboarding AI coding agents to work on an existing codebase with clear documentation
Maintaining project consistency across multiple AI sessions and human contributors
Reducing context loss and drift in long-running AI-assisted projects
Establishing a shared source of truth for requirements, design, and architecture
Template guidance should be adapted to the repository instead of applied mechanically.
Agent instruction files can shape automation behavior; review them for overbroad permissions before use.
18
Stars
3
Forks
0
Issues
MIT
License
Local code intelligence MCP server and CLI for AI coding agents, providing semantic search and call graph analysis.
MCP server that gives AI coding assistants persistent memory, semantic code search, and live telemetry.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
2 security/trust notes recorded.
Setup difficulty is 2/5.