Imbue open-sourced Catalyst to keep AI research agents exploring competing hypotheses
Kanjun Qiu and Josh Albrecht's AGPL tool beat a linear agent on nanochat, though its compute costs and research limits remain substantial.
By Ryan Merket · Published
Primary source: Imbue on X
Why it matters
Catalyst turns verification and competing hypotheses into first-class parts of an AI research workflow. If the approach generalizes beyond nanochat, small research groups could run broader computational searches without surrendering control to a closed agent platform, though token and experiment costs remain a practical constraint.
Imbue open-sourced Catalyst on July 20th, giving researchers an open-source system that preserves competing hypotheses while agents run experiments, evaluate results and search for better solutions. Imbue resurfaced the work in an August 7th thread that pointed back to the July release instead of announcing a new version.
When you purchase through links in our articles, we may earn a small commission. This doesn’t affect our editorial independence.