OSS
Nous Research's Hermes Agent Surpasses 140K Stars With Self-Improving, Skill-Creating CLI Loop
Hermes Agent from Nous Research has crossed 140,000 GitHub stars in under three months (some trackers now cite ~176k), positioned as a self-improving CLI agent with persistent memory, automated skill creation, sandboxed code execution, and support for 300+ models. NVIDIA spotlighted it running locally on RTX PCs and DGX Spark, underscoring an on-device self-improvement narrative. For builders, it's one of the most concrete open implementations of an agent that writes its own skills.
Source
↳ Follow the thread