Varietyz / Disciplined-AI-Software-Development
Disciplined AI Collaboration: a method for building software with AI. One loop at every size, rules held by checks rather than attention, state derived rather than written, evidence in place of claims. Includes the PAG grammar, an architecture and a queryable ontology. Every page is also served as Markdown and JSON at banes-lab.com.
Why this job: topics: multi-agent, agent-orchestration, ai-agents
What it does
Disciplined Methodology is a way of building software with an LLM that writes most of the code. It replaces reminders with automated checks, chat history with files in the project, and confidence with evidence. It is aimed at the problems that long projects built with a model tend to run into. Throughout the chapters, the tree means the project's files as they are on disk, and the gate means the full set of checks a change has to pass, often called a quality gate.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 35 days ago
- Stars
- 415
- On GitHub
- Licence
- CC-BY-SA-4.0
- Read the terms
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- TypeScript
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 1 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- TypeScript 100%
- CSS <1%
- WGSL <1%
- HTML <1%
Topics
- agent-orchestration
- ai-agents
- ai-assisted-development
- ai-collaboration
- ai-governance
- llm-governance
- llms-txt
- multi-agent
- ontology
- pag
- pattern-abstract-grammar
- software-architecture
Project record
- JobAgent frameworks
- StatusListed
- Commits39
- Forks34
- Watching5
- Stars in 28 days+4
- CreatedSep 4, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026