Skip to content

A framework for honest collaboration between humans and AI systems

License

Notifications You must be signed in to change notification settings

SonicField/nbs-framework

NBS Framework

A framework for honest collaboration between humans and AI systems.

Documentation

Examples

  • CLAUDE.md - Example project configuration for NBS programming

Foundation

  • Goals - The why. Everything else exists in service of this.

Pillars

Built on the foundation:

Tools

Core Command

  • /nbs - Review and dispatch

Run this after any session. It detects context and dispatches:

  • In investigation/* branch → reviews investigation rigour
  • After /nbs-discovery → verifies the discovery report is complete
  • After /nbs-recovery → reviews the recovery work
  • Otherwise → general NBS review

NBS Teams Tools

Supervisor/worker patterns for multi-agent AI work. See NBS Teams for the full overview.

Commands for setting up and using NBS teams:

For AI-as-supervisor or AI-as-worker roles:

Workflow Commands

Document Tools

Tools for working with documents - analysing, planning, and describing:

See Document Tools for the full overview.

Side Quest Commands

Run this when you want to test a hypothesis before committing to a direction. Creates an isolated investigation branch, designs falsifiable experiments, and produces a verdict (falsified / failed to falsify / inconclusive).

Verification Commands

Testing

The framework includes automated tests using a novel AI-evaluates-AI approach.

See tests/README.md for running tests.

Planning

Project plans and progress logs live in planning/:

  • <date>-<project>-plan.md - Terminal goal, completed/outstanding items, decisions
  • <date>-<project>-progress.md - Session-by-session record of what was done

Installation

git clone https://github.com/SonicField/nbs-framework.git
cd nbs-framework
./bin/install.sh

This creates ~/.nbs/ with processed commands and symlinks in ~/.claude/commands/.

For custom install location: ./bin/install.sh --prefix=/path/to/location

Author

Dr Alex Turner

Licence

MIT

About

A framework for honest collaboration between humans and AI systems

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published