calculator
An LM Studio plugin that lets LLMs evaluate math expressions using standard operators, parentheses, and JavaScript Math functions.
Discover native LM Studio plugins and MCP servers with transparent compatibility, runtime, platform, and setup information.
An LM Studio plugin that lets LLMs evaluate math expressions using standard operators, parentheses, and JavaScript Math functions.
Keeps a long chat going past the context limit, in the same window. Summarizes older messages into a consolidated state and sends the model that instead of the full history; your chat is untouched and every message stays on screen. Tool results are capped so one large call cannot kill a reply. Optionally archives transcripts and state notes to an Obsidian vault. Read 'When not to use it' first: it suits long working conversations, not bulk data analysis.
vibeLM transforms LM Studio into a 100% local, autonomous developer agent. Instead of just chatting, it gives open-weight models a registry of 38 specialized tools to plan, code, and execute development tasks completely on your own machine.What vibeLM does:Running continuous background development loops using vibe_bridge.Reading, writing, and listing files securely inside your workspace.Saving and searching notes across chat sessions so the model never forgets.Compressing chat history dynamically to prevent local VRAM lag and crashes.Running terminal scripts with a simple toggle switch to turn it off anytime.No cloud, no API keys, and no data leaks. Just pure autonomous local engineering.
Never run out of context in LM Studio: threshold-driven compaction, mid-task compression for agentic loops, tool-result capping, and Agentic Workspace state preservation.
Converts attached videos into image frames with ffmpeg before they reach the model, so any vision-capable LLM can 'watch' them. Requires ffmpeg/ffprobe and a vision model. Version 1.1 Changelog: v1.1 - Persistent frame storage (default): frames are copied to LM Studio's user-files cache so follow-up questions about the same video keep working across turns/restarts; per-chat registry tracks files. New /video commands: list, on <name>, off [name], purge <name|all>. Max 'Frame count' and 'Max frames per video' raised from 100/400 to 1000. v1.0 - Initial release: ffmpeg frame extraction (fixed-FPS or fixed-count sampling, resolution cap) for vision models.
Persistent memory system for LM Studio. Stores global and per-chat facts in ~/.lmstudio/memories/, auto-injects them into every prompt, and provides tools to read, write, and remove line-based memories — with intelligent scope selection and unambiguous AI/User labels. https://github.com/esalesninja/memory
Version 5.3.3
No description provided on LM Studio Hub.
No description provided on LM Studio Hub.
No description provided on LM Studio Hub.
No description provided on LM Studio Hub.
A web tools plugin for LM Studio built on the impit client for improved bot detection evasion. Includes a Visit Website tool and Web Search backed by DuckDuckGo. An LM Studio plugin that gives local LLMs four web-oriented capabilities: searching the web, searching for images, visiting a page and reading its content, and downloading images into the chat's working directory so the assistant can embed them inline.
No description provided on LM Studio Hub.
OpenAI-compatible endpoint plugin updated by Sonct. Adds Claude, OpenAI, Deepseek, GLM, and custom model routing.
Inspect, trim, convert, and manage FFmpeg video jobs locally from LM Studio.
This plugin enables large language models in LM Studio to perform file and directory operations through a set of safe, controlled tools. It bridges the gap between AI assistants and the file system while maintaining security through path traversal protection.
No description provided on LM Studio Hub.
Next-level image search and information retrieval based on multimodal embeddings. find-image supports text-based, image-based, and metadata-based queries using Qwen3-VL-Embedding.
No description provided on LM Studio Hub.
v1.0.0
No description provided on LM Studio Hub.
complete Web Search
All-in-one LM Studio plugin: 50+ local tools, persistent memory, sub-agent delegation, design systems, and media analysis. Modular architecture with smart output caps on all tools, near-duplicate memory detection (TF-IDF + Jaccard), HTML asset auditing, tiered memory injection (L0 identity → L1 essential → L2 contextual), 58 pre-cached design system references, pattern-matched delegation hints (EN/PT), and auto hints that guide local models to use efficient editing patterns. Optimized for models with limited context (4K-20K tokens).
No description provided on LM Studio Hub.
Fork of Altra web-search - Fact-grounded web search with source verification — searches the web, reads full pages, fact-checks claims, and flags single-source info as unverified. No API key required. Fixes oriented on stability and reliability - especially around default DDG/Bing scrapers.
Give your local model web search. DuckDuckGo backend works out of the box (no API key); SearXNG backend lets you point at your own privacy-respecting metasearch instance (Google Bing Brave DuckDuckGo combined).
Advanced LM Studio plugin for DuckDuckGo web and image search with retries, URL normalization, fallback image extraction, and local thumbnails.
No description provided on LM Studio Hub.
No description provided on LM Studio Hub.
Advanced LM Studio plugin for current datetime, timezone-aware timestamp interpretation, and relative time comparison.
Advanced LM Studio plugin for listing and analyzing local images with vision-capable models.
No description provided on LM Studio Hub.
A lean, fast-path terminal plugin for LM Studio. https://github.com/imezx/terminal
A deep research engine with RAG for LM Studio, built around a Kimi-style Agent Swarm. Dynamically spawned specialized worker agents run in parallel, coordinating through shared state to produce a comprehensive, cited research report with contradiction detection — in a single tool call. https://github.com/imezx/deep-swarm-research-plugin
No description provided on LM Studio Hub.
AI Toolbox — LM Studio Plugin 109 tools across 17 categories: file system, web research, browser automation, Git/GitHub, database, document parsing, background commands, code execution, utilities, image processing, HTTP client, vector RAG, text processing, interactive UI generation, auto-context management, backup & restore, and line operations.
Big RAG Plugin for LM Studio A powerful RAG (Retrieval-Augmented Generation) plugin for LM Studio that can index and search through gigabytes or even terabytes (not tested) of document data. Hosted here: github.com/ari99/lm_studio_big_rag_plugin
Give your local LLM a long-term brain. This plugin stores facts, preferences, projects, and notes across conversations in a local SQLite database — zero cloud, zero external services, fully portable. https://github.com/imezx/persistent-memory-plugin
Turns your own documents into an interlinked markdown wiki that the plugin builds and curates itself, then answers questions from it through a local-embedding RAG layer (hybrid semantic + keyword search). Ingests .md, .txt, .docx and .pdf; runs fully offline. By Rodrigue Beck.
Sandboxed Claude-Code-style toolkit for local models: orient, grep, surgically edit, run and watch processes, read git, fetch docs, and track a checklist inside one folder. Every capability is off by default.
Autonomous coding agent for LM Studio: plans, edits transactionally with rollback, runs commands, uses Git/GitHub, researches the web, runs sub-agents. Manual/Plan/Auto approval.
Gemini Pro Image Compatibility Endpoint for LM Studio
A lean, fast-path terminal plugin for LM Studio. https://github.com/imezx/terminal
A LM studio plugin to allow your LLM to search the web to get up to date and relevant information
Secure IMAP and SMTP email tools with relative-date search, protected credentials, and opt-in send and Trash capabilities.
OpenAI-compatible endpoint plugin updated by Sonct. Adds Claude, OpenAI, Deepseek, GLM, and custom model routing.
This project is a plugin for LM Studio that provides a rich set of tools to the large language model. It allows the LLM to interact with your local file system, execute code, access the internet, and more. This empowers the LLM to perform complex tasks like code generation, project scaffolding, and web research.
Transcribe PDFs to Markdown using whichever vision-language model is loaded in LM Studio (tested with Qwen3-VL). Each page is rasterized locally and read by the VL model — no OCR install, no Python, no cloud.