0.87.0
KalyanKS-NLP/llm-engineer-toolkit0.87.0Sep 25, 2026by takahirom
Upgrading?
AI Summary
Reduces view hierarchy fetches per step by reading the screen once per step and reconnecting on failure instead of probing.
Key Highlights
- Hierarchy fetches reduced per step
- Reconnection on failure instead of probing
New Features
- Screen reads reduced from 11-13 to 3-4 per step
- Step elements come from one hierarchy fetch
Full Release Notes
Each step now reads the device screen with far fewer view hierarchy fetches, which cuts non-AI time per step. On an Android emulator, reading the screen went from about 1.4s to 0.2–0.4s per step, and hierarchy fetches went from 11–13 to 3–4 per step. ## Fewer Hierarchy Fetches per Step (#452, #453) - Reads no longer check the connection with an extra hierarchy fetch first. A read that fails reconnects and is retried. Actions keep the up-front check, so a tap or key press that failed part way is not repeated blindly. - A step's elements, UI tree and focused element now come from one hierarchy fetch, so they always describe the same frame. ## What's Changed * Reconnect on a failed device read instead of probing before every read by @takahirom in https://github.com/takahirom/arbigent/pull/452 * Read a step's elements, tree and focus from one hierarchy fetch by @takahirom in https://github.com/takahirom/arbigent/pull/453 **Full Changelog**: https://github.com/takahirom/arbigent/compare/0.86.0...0.87.0
Related Repositories
public-apis/public-apis★ 491,139
A collective list of free APIs
openclaw/openclaw★ 392,706
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
nilbuild/developer-roadmap★ 370,074
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
morluto/rea★ 358,288
Reverse engineer anything with agents, from app behavior down to native binaries.
obra/superpowers★ 303,182
An agentic skills framework & software development methodology that works.