Open Issues Need Help
View All on GitHub benchmarks: Modernize Terse Mode benchmark script with current GenAI SDK and full prompt suite 17 days ago
enhancement good first issue
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