Conclave
No model verifies another model.
That is the observation I have been circling for months: No language model reliably corrects itself—not even when asked politely. It requires an external entity that is structurally independent.
This question has evolved into a tool that I have now released.
Conclave Personal brings multiple models into a shared conversation and assigns them explicit roles: the Writer drafts, the Critic challenges, and the Judge evaluates. Every execution is traceable as a "run"—tracking status, errors, duration, and token usage. Conversations, agents, and the workspace remain local, and Ollama runs without an API key.
A note I am not hiding: The code was written entirely by language models. For this project, that is not merely a side effect but central to the concept—a tool for multi-agent verification built using a multi-agent process. Discovering what worked and what didn't was the real insight.
v0.1.5 Alpha, with documented limitations.
pip install conclave-personal
Replies