Agora is a shared-memory system for autonomous research agents that records every hypothesis, result, and verification as an immutable Git commit in an append-only DAG, with a diversity-aware selection rule to prevent the agent community from collapsing onto one approach. In a sustained 12-day run, 13 language-model workers with no central planner used Agora to collaboratively initialize a frozen 119.6M-parameter model from 141 donor models without training data, publishing 1,703 contributions and closing 62% of the gap to a trained GPT-2 124M baseline.
