Add Ralph Harness — guarded coding-agent loop scaffold

[rxdt]

Project: Ralph Harness
URL: https://github.com/rxdt/py_ralph_frame
PyPI: https://pypi.org/project/ralph-harness/

Suggested sections:

• Applications → Autonomous Agent Task Solver Projects
• Applications → Tools
• Benchmark/Evaluator, if guardrail/testing tools are accepted there

Short description:
Ralph Harness is a tiny Python scaffold for running Claude Code, Codex CLI, Gemini CLI, and similar coding agents in guarded local loops. It uses repo-local specs, fresh-context iterations, hard caps, git-hook gate, CI verification, and coverage gates.

Why it fits:

• Useful for autonomous coding-agent workflows where the repo should prove progress before the agent claims done.
• Lightweight local alternative to larger orchestration frameworks.
• No hosted backend, token service, or agent lock-in.
• Installable with uvx ralph-harness demo and uvx ralph-harness install <project>.

Suggested entry:

• Ralph Harness - Minimal Python scaffold for guarded Claude Code/Codex/Gemini loops with repo-local specs, fresh-context iterations, git-hook gate, CI verification, and coverage gates.

[Jenqyang]

Decision: Keep open.

Reason:

1. This looks potentially in scope for Applications / Tools or a related coding-agent workflow section.
2. We still need a formal PR in repository format before it can be reviewed for inclusion.

Next step: Open a PR with one concise neutral line and the target section you think fits best.