Konsey
ストックにはログインが必要です
Multi-LLM council where a model can't verify its own output
Artificial Intelligence
Developer Tools
GitHub
Trusting a single LLM to grade its own answer is a conflict of interest. Konsey runs several models as a council: independent providers each plan, an adversarial critic attacks the plans, and a different provider verifies the result. The producer never verifies its own output. Vendor-neutral (Claude/Codex/Gemini or local Ollama), local-first, layered PHI/KVKK-aware safety, MIT-licensed.
投票数: 3