v0.6.21
mudler/LocalAIv0.6.21Oct 2, 2026by RasulOs
Upgrading?
AI Summary
This release updates model support by adding GPT-6.1-sol and Claude-sonnet-5-5 while removing GPT-5.5 and retired DeepSeek aliases. It also fixes vision coordinate parsing for Gemma, Gemini 3.8 Flash, and Sonnet 5, and resolves an issue with whitespace in open_app identifiers.
Key Highlights
- Fixed model-specific vision coordinates for Gemma, Gemini 3.8 Flash, and Sonnet 5
- Added support for GPT-6.1-sol and Claude-sonnet-5-5
- Dropped GPT-5.5 and retired DeepSeek model aliases
- Fixed whitespace stripping from open_app identifiers
Breaking Changes
- Dropped GPT-5.5 model
- Removed retired DeepSeek model aliases
New Features
- Added GPT-6.1-sol model support
- Added Claude-sonnet-5-5 model support
- Fixed vision coordinates for Gemma, Gemini 3.8 Flash, and Sonnet 5
- Fixed whitespace stripping from open_app identifiers
Full Release Notes
## What's Changed * fix: model-specific vision coordinates for Gemma, Gemini 3.8 Flash and Sonnet 5 by @RasulOs in https://github.com/droidrun/mobilerun/pull/465 * feat: add gpt-6.1-sol and claude-sonnet-5-5, drop gpt-5.5 by @RasulOs in https://github.com/droidrun/mobilerun/pull/468 * chore: drop retired DeepSeek model aliases by @RasulOs in https://github.com/droidrun/mobilerun/pull/469 * fix: strip whitespace from open_app identifiers by @RasulOs in https://github.com/droidrun/mobilerun/pull/471 * chore: release mobilerun 0.6.21 by @RasulOs in https://github.com/droidrun/mobilerun/pull/472 * chore: merge develop into main for 0.6.21 by @RasulOs in https://github.com/droidrun/mobilerun/pull/473 **Full Changelog**: https://github.com/droidrun/mobilerun/compare/v0.6.20...v0.6.21
Related Repositories
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
The world’s fastest framework for building websites.