Hermes Agent Tops OpenRouter; Xiaomi MiMo Leads Models

admin

10 May 2026 — 1 min read

Hermes Agent has overtaken OpenClaw to claim the top spot on OpenRouter’s global app token consumption ranking, processing 271 billion daily tokens—a milestone that underscores the shift toward real-world, complex tasks being executed by open-source autonomous agents.

Daily Token Leader: Hermes Agent Surpasses OpenClaw on OpenRouter

According to the latest OpenRouter data, Hermes Agent now leads all global applications in token consumption, reaching 271 billion tokens per day. This marks the first time it has surpassed OpenClaw, a previously dominant closed-source agent, in daily usage volume.

Contributing Models: Xiaomi’s MiMo-V2-Pro Leads the Pack

Among the models fueling Hermes Agent's token consumption, Xiaomi's MiMo-V2-Pro contributed the most, followed by MiniMax, NVIDIA, Stepfun, and Tencent. The diversity of contributing model vendors highlights the ecosystem’s reliance on multiple open-source backends rather than a single proprietary foundation.

Persistent Memory and Self-Learning Drive Adoption, GitHub Stars Soar to 140k

Hermes Agent’s architecture features persistent memory and a self-learning mechanism, enabling it to retain context across sessions and adapt to user behavior over time. This functionality has resonated with developers, causing its GitHub repository to double from previous levels to 140,000 stars.

Open-Source Agents Challenge Closed-Source Incumbents Amidst Stability and Cost Trade-Offs

Industry analysts note that high token consumption reflects real users engaging in complex, multi-step tasks rather than simple queries. Open-source agents like Hermes are now competing with closed-source code assistants by demonstrating actual usage in production environments. However, the reliability, cost efficiency, and task success rates of these systems remain critical balancing factors for sustained adoption.

NVIDIA and SK hynix Partner on AI Factory Memory

NVIDIA and SK hynix have entered a multiyear technology partnership to co-develop next-generation memory specifically designed for AI factories, aligning tightly with NVIDIA’s infrastructure roadmap. The collaboration spans memory for Vera Rubin supercomputers, Vera CPUs, RTX Spark PCs, and Jetson Thor robots, marking a deep integration between chip design

Goose: AI agent runs code, not just suggests

The Linux Foundation has officially unveiled Goose, an open-source AI agent that marks a paradigm shift from advisory tools to autonomous code execution, capable of installing, editing, testing, and running code without human intervention. Built in Rust and boasting over 70 extensions via the Model Context Protocol, Goose connects to

Accenture: Enterprise AI Reaches Scale in 2026

Enterprise AI is approaching a critical inflection point in 2026, as Accenture predicts a transition from experimental pilots to large-scale deployment, with customer-facing AI solutions and agentic systems moving into production. However, three major barriers—data infrastructure and cloud migration, enterprise knowledge bases, and governance plus workforce transformation—must be

Kimi Work Beta: Smarter Office Agent for Chinese Workplace

Chinese AI startup Kimi has launched Kimi Work, a local universal agent specifically designed for knowledge workers, offering a pragmatic alternative to broad-spectrum AI assistants. Early beta test results reveal strong performance in routine office tasks like report generation and data collection, though advanced capabilities remain behind a paywall. Kimi