7 projects
modeldiffr
Audit what changed between a base LLM and any fine tune, quant, merge, or edit.
gitgrounded
Auto generated benchmarks, change targeted regression tests and signed, verifiable reports for LLM apps, prompts, models and MCP servers
rungated
Python SDK for the Rungated runtime AI agent firewall
bitnarrow
Open weight model surgery lab: edit, measure, gate, and ship LLM transformations
issueloop
Finds failing tests, splits failures into independent tickets, stores them, hands them out one at a time.
truenorth-framework
Conversation-first AI agent framework.
check-working
A simple example package
