Prime Agent: An Open-Source Harness for Self-Improving RLM

PrimeIntellect · hf · 2026-08-25

Prime Agent is an open-source harness that uses recursive subagents, persistent computation, and agent-to-agent coordination to extend language models' long-horizon capabilities across coding and reasoning tasks.

Related event: Prime Agent Open-Sourced, Lifting ARC-AGI Score to 95.5%(4 posts)→

Original post →

More from coding & agent

coding & agent channel →