5arXiv cs.CL (Computation and Language)·
PalmClaw: Open-source native on-device LLM agent framework for mobile phones
PalmClaw is an open-source agent framework that runs LLM agents natively on mobile devices, managing sessions, memory, skills, tools, and the agent loop entirely on-device. Unlike existing mobile agents that rely on GUI actions (tapping, swiping), PalmClaw exposes device capabilities as structured tools with explicit arguments and execution boundaries, enabling more direct and controlled access to device features. Experiments report an 11.5% relative improvement in task success rate and a 94.9% reduction in completion time over the strongest baseline.
Related guides (2)
Related events (8)
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.
KnowAct-GUIClaw: Self-evolving memory and skill framework for cross-platform GUI agents
Researchers introduce KnowAct-GUIClaw, a Know-Route-Act-Reflect agent framework extending the OpenClaw agent system with cross-platform GUI interaction support across Android, iOS, HarmonyOS, and Windows. The system features an experience-attributable memory system and self-evolving skill library that continuously improves from user interaction history. Using open-source Kimi-2.6 models, the framework achieves 64.1% on the MobileWorld long-horizon benchmark, reportedly outperforming closed-source agentic models including GPT-5.5 and Seed-2.0-Pro. The transferable memory and skill components provide an 8.5% improvement when applied across different base models.
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.
MaskClaw: Edge-Side Privacy Arbitration System for GUI Agents with Behavior-Driven Skill Evolution
MaskClaw is an edge-side privacy arbitration framework for GUI agents that intercepts screenshots before they leave a trusted environment, applying Allow/Mask/Ask decisions based on local visual evidence and user-specific policy memory. The system addresses the gap where static PII detectors miss context-dependent privacy boundaries and cloud-side VLMs may upload raw screens before deciding what to protect. The authors introduce P-GUI-Evo, a new benchmark built from real UI patterns and sanitized labels, and demonstrate that pattern matching, cloud reasoning, and routing alone each exhibit systematic failure modes. The artifact is open-sourced on GitHub.
nanoclaw: lightweight containerized agent framework built on Anthropic's Agents SDK
nanoclaw is an open-source TypeScript project positioning itself as a lightweight, security-focused alternative to OpenClaw, running in containers. It integrates with WhatsApp, Telegram, Slack, Discord, and Gmail, and includes memory and scheduled job capabilities built on Anthropic's Agents SDK. The project has accumulated nearly 30,000 GitHub stars, suggesting significant community traction.
RealClawBench: Live benchmark framework built from real developer-agent sessions
RealClawBench is a new benchmark framework that converts real OpenClaw developer-agent sessions into reproducible, automatically scored evaluation tasks. It addresses realism gaps in existing agent benchmarks through reconstructed execution environments and deterministic verifiable scorers, releasing 281 executable tasks sampled to preserve the source session distribution. Evaluation of 14 contemporary models shows the best system solves only 65.8% of tasks, indicating substantial headroom on realistic developer-agent workloads.
SpatialClaw: Code-as-action interface for agentic 3D/4D spatial reasoning with VLMs
SpatialClaw is a training-free framework that uses code execution as the action interface for vision-language model agents performing spatial reasoning tasks. The system maintains a stateful Python kernel with perception and geometry primitives, allowing the VLM to write iterative executable cells conditioned on prior outputs rather than committing to a full strategy upfront. Evaluated across 20 spatial reasoning benchmarks covering static and dynamic 3D/4D tasks, SpatialClaw achieves 59.9% average accuracy, outperforming the prior state-of-the-art spatial agent by +11.2 points across six VLM backbones.
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.