Decision information
Verified: 8/14/2026- Ecosystem category
- Research & Benchmarks
- Provider
- LiberCoders
- Content type
- Research
- Pricing
- Open Source
- Open source
- Yes
- License
- Not recorded
- Maintenance
- Active
- Install methods
- Source
- Platforms
- Linux, Docker
Security signals (informational, not a security certification)
Source availableRequires shellRequires browser access
Verification source: https://arxiv.org/abs/2605.26086 · arXiv:2605.26086
Overview
A benchmark for always-on personal assistants that measures long-horizon event understanding, interconnected digital services, and cross-device GUI and CLI interaction.
What it provides
- Models a broader slice of a user's digital world
- Evaluates long-horizon history, backend services, and devices
- Includes benchmark environments and an automated data-generation pipeline
AllClaw classification
This project supports the Claw ecosystem as research benchmarks; it is not presented as a standalone Claw agent.
Provider: LiberCoders. Primary source: https://arxiv.org/abs/2605.26086.
The classification and core claims were checked against the linked primary source on August 14, 2026.
Tags
benchmarkalways-onpersonal-assistantguiclievaluation