Release Newelle 1.5.0 · qwersyk/Newelle

Modes Support

MCP Servers Catalog	Mini Window Mode	Extensions and Skills Catalog

Integrated Skill Editor	Interactive Terminals	Citations

🖥 Improved terminal tool — Newelle can now manage persistent Terminal sessions and interact with TUIs.
💫 Mode switching — users can now create custom "modes" that quickly change prompts, tools and skills (e.g. Planning mode).
📲 MCP Servers catalog — added a curated catalog of MCP servers that can be used to connect your applications to Newelle.
🌐 Citations — the LLM can now state the source of information.
➕ LLM provider management — you can now add LLM providers directly from the UI (OpenAI/Ollama/Anthropic compatible).
🚀 Improved text generation animation.
🔻 Compact Mode — added a compact mode for tool calls and the input bar.
🧩 Extensions and Skills catalog — you can now download and explore new extensions and skills directly in Newelle.
✏️ Skill editor — create and edit Newelle Skills directly from Newelle.

Added a send_message tool for sending messages to interfaces, such as "send me this on Telegram".
Added new tools: sleep and switch_mode.
Agents can now read images using the read_image tool.
Vision chats can now be delegated to a secondary LLM.
Added support for Mistral STT and TTS.
Added API key support for Ollama.
Improved Anthropic's LLM handler.
Added the ability to set the maximum number of tool iterations in a chat.
Fixed bugs with the OpenAI handler.
Added support for the OpenAI /responses endpoint.
Improved the Telegram interface.
Improved the GUI-API interface.
Improved logging support in the OpenAI API interface.
Fixed bugs with LaTeX rendering and improved performance.
Added an option to automatically expand thinking.
Fixed thinking scrolling up while streaming.
Improved mini-window mode.
Added CTRL+G to switch between normal and mini-window modes.

Contributors

Full Changelog: 1.4.5...1.5.0