3 projects
triple-check-verify
Stop local LLMs making up numbers: Python does the math, two experts explain it, a different model verifies every figure against a fact base.
launchd-doctor
Find and fix the macOS LaunchAgent bugs that fail silently, plus a circuit breaker for agents that keep failing.
ollama-council
Adaptive multi-model council for local Ollama models: two models cross-check, a third breaks ties.