From AI to Chitta
Tools for working with AI in a way that can be checked: Claude Code plugins, LLM security scanning, and frameworks for architecture, cost and practice.
From AI to Chitta — open
Tools for working with AI in a way that can be checked.
Everything here comes out of daily practice as an AI advisor. Repositories are added when they are good enough to depend on.
Claude Code plugins
None are published right now. A plugin is listed here again when it is good enough to depend on.
Python libraries
| Repo | What it does | Maturity |
|---|---|---|
| llm-ingestion-pipeline-security | Write-time defensive layer for Python pipelines that persist LLM output | beta |
Maturity labels
Every repo carries a status-* topic, and the table above reads from it.
stable is in daily use and safe to depend on. beta works and is in use,
with an interface that may still move. alpha is early and will change.
experimental is research — read it, do not build on it yet.
Install
Python libraries. These are not on PyPI. llm-ingestion-pipeline-security
is installed with pip under the name llm-ingestion-guard, from a release tag
or from the Forgejo package index — the exact commands are under Install in
its README.
License and security
MIT unless a repo says otherwise. Security contact: SECURITY.md.
More context and writing at fromaitochitta.com.