DivyamTalwar/fablewright
Risk-gated multi-model orchestration for Claude Code and OpenAI Codex. Claude Fable 5.1 writes the spec and accepts the result; pinned GPT-5.6, DeepSeek and GLM lanes perform it; reviewed routes add a fresh read-only reader, cross-family wherever one is callable. Every model pin is proven against runtime evidence, not assumed.
Shell
2
2 contributors
MIT License
Social mentions
Recent discussions about this repository across the web
Repository activities
repository's daily and monthly activities across stars, forks, merged PRs, issues, and closed issues