Forked from beledarian/beledarians-lm-studio-tools
Project Files
README.md
This project is a plugin for LM Studio that provides a rich set of tools to a large language model. It acts as a bridge between the LLM and your local environment, enabling autonomous coding, research, and file management.
[!IMPORTANT] LM Studio does NOT support automatic updates. If you encounter issues, please try manually updating first by removing the current version and re-downloading from the plugin website. LM Studio may show an "already installed" tooltip, even if your version is outdated.
replace_text_in_file to make surgical edits instead of rewriting large files.save_file supports creating multiple files in one go.delete_files_by_pattern to wipe temporary files instantly.Encountering issues? Feel free to submit them on GitHub.
Find this project helpful? Consider giving it a ⭐ on GitHub or contributing! Thank you for using the toolbox.
[!WARNING] Enabling shell or terminal execution allows the model to run arbitrary commands on your system. If enabled, the model may be able to modify files and escape the sandbox environment.
browser_session_open/control/close flow for multi-step browsing and automation.rag_local_files).💡 Tip: Need persistent long-term memory for your agent? Check out my other project: Local Memory MCP – A privacy-first memory server with knowledge graph support.
The plugin can be installed using the following link:
https://lmstudio.ai/beledarian/beledarians-lm-studio-tools
Alternatively, you can install it manually for development purposes.
If you want to contribute to the development of this plugin, you can follow these steps:
Clone the repository:
Install dependencies:
Access these settings in the LM Studio "Plugins" tab:
consult_secondary_agent: The powerhouse tool. Delegates tasks, handles file creation, and manages sub-agent loops.run_javascript, run_pythonexecute_command (Background), run_in_terminal (Interactive)rag_local_files: Search your code.save_memory: Long-term memory.get_system_info, read_clipboard, write_clipboardSee CODE_OVERVIEW.md for architectural details.
Browser Reliability and Navigation Context
browser_session_open returns full page text by default (include_page_text defaults to true)Sub-Agent Compatibility Improvements
subagent_docs.md is automatically loaded into the contextconsult_secondary_agentbeledarian_info.mda.Link--primarybrowser_session_open now returns full page text by default for better multi-step planning.parameters format (e.g., Gemma 4)handoff_message support for relaying findings/researchhandoff_message for the main agent to relay findings/research.beledarian_info.md to understand your project's history.Run in development mode: From within the project directory, run the following command:
This will start the plugin in development mode. LM Studio should automatically pick it up. Any changes you make to the source code will cause the plugin to automatically reload.
Allow Browser Control + Sub-Agent: Allow Web Search + Sub-Agent: Allow Browser Control.list_directory, change_directory, make_directoryread_file, save_file (supports batch), delete_pathreplace_text_in_file: Precision editing.delete_files_by_pattern: Regex-based cleanup.move_file, copy_file, find_files, get_file_metadatafuzzy_find_local_files: Levenshtein-based fuzzy file path/name search.web_search (DuckDuckGo API + HTML fetch/browser fallback), wikipedia_searchfetch_web_content, rag_web_contentbrowser_session_open, browser_session_control, browser_session_close (persistent page automation; preferred for multi-step navigation, with deduped page-text output unless full_read=true)browser_open_page (stateless one-shot Puppeteer read)evaluate action to click by text, then call with full_read=true.browser_session_open → browser_session_control → browser_session_close{"tool": "...", "parameters": {...}} format now work correctly with consult_secondary_agentbrowser_session_open, browser_session_control, browser_session_close) including in-page fuzzy find and URL-change noticeshandoff_message) for relay/summary workflows{file_name, content} JSON format from some modelsgit clone https://github.com/Beledarian/Beledarians_LM_Studio_Toolbox.git
cd Beledarians_LM_Studio_Toolbox
{
"actions": [
{
"type": "evaluate",
"script": "const link=[...document.querySelectorAll('a')].find(a=>a.textContent?.includes('LICENSE')); if(link) link.click();"
}
],
"full_read": true
}
npm install
lms dev