Contribute
Where to contribute
| Platform | Role |
|---|---|
| GitHub / TunedChaos | Primary public host - open issues and pull requests here |
| GitHub Sponsors | Support the project |
Full topology: Repository architecture.
Public repositories (alpha launch)
Contribute against these public GitHub repositories:
- chaosnexus-anvil
- chaosnexus-forge
- chaosnexus-website
- chaosnexus-codex
- chaosnexus-crucible - local LLM interface (not model weights). Docs: About Crucible
- chaosnexus-scripts - shared Rhai plugins/libs. Docs: About Scripts
- chaosnexus-tuned - dataset generation, eval, and fine-tuning pipeline (weights stay out of git; adapter on Hugging Face)
- chaosnexus-suite - Suite packaging and Release landing
Model weights: TunedChaos/ChaosNexus_Tuned_v1 (PEFT / LoRA on Granite 4.1-8B).
Ground rules
- Read SECURITY.md / component
SECURITY.mdbefore filing security findings (email security@tnd.cx for undisclosed issues). - Accept the dual-license contributor grant in each repo's
CONTRIBUTING.md. - Read the AI assistance disclosure. If you use generative tools in a PR, disclose that you used AI assistance and keep diffs reviewable.
- Prefer small, focused PRs with semantic commit messages.
- Expect delays in responses; GitHub issues are the right inbox.
AI agents indexing docs
Agents should start at AI agents (/llms.txt, optional Cloudflare AI Search MCP). Documentation is AGPL-3.0-or-later; see Licensing and Privacy.
Dev blog
News: tunedchaos.dev