A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

ai-safety anthropic claude claude-fable claude-fable-5 fable-5 finops gemini guardrails llm openai proxy python security token-optimization
1 Open Issue Need Help Last updated: Oct 4, 2026

Open Issues Need Help

View All on GitHub

A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

Python
#ai-safety#anthropic#claude#claude-fable#claude-fable-5#fable-5#finops#gemini#guardrails#llm#openai#proxy#python#security#token-optimization