Hermes Agent Surpasses OpenClaw in Daily Token Usage, Highlighting Self-Improving Agentic Capabilities
Hermes Agent, an open-source personal agent from Nous Research launched in February 2026, has overtaken OpenClaw on OpenRouter's daily token consumption leaderboard. It distinguishes itself through automatic skill creation (converting successful task completions into reusable SKILL.md instruction files), a two-tier memory architecture with intelligent deduplication and merging, and a Curator background process that manages skill lifecycle. The agent supports local or cloud deployment, integrates with ~20 messaging services, and works with a wide variety of LLMs, positioning it as a model-agnostic alternative in the emerging personal agent category.
Related guides (4)
Related events (8)
Hermes Agent Challenges OpenClaw on Token Usage Leaderboard; Agent Self-Improvement Highlighted
Hermes Agent, an open-source AI agent from Nous Research launched in February 2026, has surpassed OpenClaw on OpenRouter's daily token consumption leaderboard. Hermes Agent differentiates itself through a memory architecture and automatic skill-building capability using the SKILL.md format, enabling self-improvement as a core agentic feature. It supports local and cloud deployment, integrates with ~20 messaging services, and works with a wide variety of LLMs via the Agent Communication Protocol. The piece also covers Andrew Ng's commentary on Harvard's grade-capping policy, which is tangential to AI/ML.
Hermes Desktop: open-source desktop companion for Hermes Agent gains traction on GitHub
Hermes Desktop is a TypeScript-based open-source desktop application serving as a companion interface for the Hermes Agent. The repository has accumulated over 10,000 stars with 417 added in a single day, suggesting significant community interest. The project appears to be a local/desktop agent harness in the growing ecosystem of open-source AI agent tooling.
NousResearch/hermes-agent: Trending Python Agent Framework
NousResearch has published hermes-agent, a Python-based agent framework described as 'the agent that grows with you.' The repository is trending heavily on GitHub with 161,088 total stars and 1,923 stars added today, indicating significant community interest. The project appears to be an agentic system built around NousResearch's Hermes model line.
Anthropic launches Claude Mythos 5 and Claude Fable 5; Andrew Ng introduces OpenCoworker desktop agent
Anthropic released Claude Mythos 5 and Claude Fable 5, two variants of the same frontier model that set new state-of-the-art results across software engineering, knowledge work, cybersecurity, and agentic coding benchmarks. Claude Fable 5 is the general-availability version with safety classifiers that restrict responses on security, biology, chemistry, and cutting-edge AI topics, priced at $10/$50 per million input/output tokens; Mythos 5 is restricted to selected partners via Project Glasswing. Separately, Andrew Ng and collaborators released OpenCoworker, a free open-source desktop agent harness built on top of aisuite, designed to give users privacy-preserving agentic workflows with their own API keys or local models. The newsletter also contextualizes the broader shift toward LLM-driven agent harnesses as frontier models have become capable enough to reliably drive next-action decisions.
NousResearch Hermes Paperclip Adapter: Run Hermes Agent as a Managed Employee
A TypeScript adapter enabling NousResearch's Hermes agent to operate within the Paperclip company management framework, effectively treating the AI agent as a managed employee. The project has accumulated 1,311 GitHub stars with 37 added today, suggesting moderate community interest. This represents a tooling integration in the agent-as-worker paradigm, connecting an open-weights model ecosystem to an enterprise-style agent orchestration layer.
Anthropic Releases Claude Opus 4.5 with State-of-the-Art Coding, Agent, and Computer Use Capabilities
Anthropic has released Claude Opus 4.5, positioning it as the best model in the world for coding, agentic workflows, and computer use, with pricing reduced to $5/$25 per million input/output tokens. The model demonstrates significant token efficiency gains—up to 65% fewer tokens than prior models on equivalent tasks—alongside improvements in long-horizon autonomous task execution, multi-step reasoning, and self-improving agent behavior. The release is accompanied by updates to Claude Code, the Claude Developer Platform, and integrations with Excel, Chrome, and desktop environments. Early partner feedback from GitHub Copilot, Cursor, Notion, Warp, and others reports measurable benchmark improvements and new use cases previously out of reach.
Claw-Anything: Benchmark for Always-On Personal Assistants with Broad Digital World Access
Claw-Anything is a new benchmark designed to evaluate LLM agents acting as always-on personal assistants with access to long-horizon activity histories, interdependent backend services, and multi-device GUI/CLI interaction. The benchmark simulates months of user activity to create complex, noisy world states and evaluates both reactive and proactive assistance. GPT-5.5 achieves only 34.5% pass@1, revealing a substantial capability gap versus prior narrower benchmarks. An accompanying automated data-generation pipeline produces 2,000 training environments and yields a 23.7% improvement over the base model.
NVIDIA NemoClaw: Secure agent execution inside NVIDIA OpenShell with managed inference
NVIDIA has published NemoClaw, a TypeScript project on GitHub for running AI agents such as Hermes and OpenClaw more securely inside NVIDIA OpenShell with managed inference. The repository has accumulated over 20,000 stars, suggesting notable community interest. The project appears to be part of NVIDIA's broader NeMo ecosystem for enterprise AI agent deployment.