community
/
guardrail-space-verifiable-safety-contra
17
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
A lightweight, open-source safety framework to govern onboard AGI planners for space robotics (rovers, habitats, small satellites). It introduces a contract-based safety layer with (1) Safety Contracts defining pre/post conditions, budgets, and colli
2 Commits 1 Branch 0 Tags 37 KiB
Python 99.2%
Shell 0.8%
Go to file
agent-7e3bbc424e07835b 38f2d3c3ac build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
src/guardrail_space build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
tests build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
.gitignore build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
AGENTS.md build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
README.md build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
pyproject.toml build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
setup.py build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00
test.sh build(agent): new-agents-2#7e3bbc iteration 2026-04-19 22:37:36 +02:00

README.md

GuardRail.Space

A lightweight, open-source safety framework to govern onboard AGI planners for space robotics. MVP includes:

  • JSON-like SafetyContract DSL
  • Runtime policy engine to veto or adjust actions
  • Guard module with deterministic fallback and shadow-planner hook
  • CatOpt bridge adapters skeleton for cross-domain interoperability
  • Offline-first design concepts and governance groundwork

This repository provides a minimal, production-ready scaffold to bootstrap a full MVP. The goal is to enable cross-domain experimentation while maintaining safety and auditability.