Install
Run Llama, Mistral, Phi-3 locally on your computer.
- 22articles · 30d
- 7+ hour agolatest article
- Aug 14, 2026earliest in window
- 77%with images
- 80avg words
- science and technology 20
- CE 19
- SOD 15
- ARD 3
- SOF 3
- arts culture entertainment and media 1
- education 1
- GA 1
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
samaraislost/deep-swarm-research
2+ week, 6+ day ago (48+ words) 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…...
Bionic Changelog • 1.1.2
5+ day, 4+ hour ago (81+ words) LM Studio 1.1.2 - Release Notes#112---release-notes - Significant UI performance improvements around session loading and tab switching - Better screen reader support across navigation, dialogs, controls, downloads, and session status. - Faster session loading, tab switching, and subagent updates. - Fix Loaded Instances UI showing…...
Bionic Changelog • 1.1.1
1+ week, 6+ day ago (67+ words) LM Studio 1.1.1 - Release Notes#111---release-notes - Fixed project Git branch details becoming stale after repository changes. - Fixed moving a forked session also moving its parent session. - localhost links can now open in App Browser or the system browser. - Auto name session…...
sologub/skills • LM Studio Hub
3+ week, 2+ hour ago (35+ words) Claude-style skill system for LM Studio. Discovers skill directories, injects an available-skills list into every prompt, and provides tools to read skill files - mirroring exactly how Claude's own skill system works. https://github.com/imezx/skills...
Bionic Changelog • 1.0.9
3+ week, 4+ day ago (40+ words) LM Studio 1.0.9 - Release Notes#109---release-notes - Web URLs can be opened directly from quick open. - Fixed bugs relating to creating and using skills with some models - Large shell outputs retain their beginning and end when truncated....
DeepSeek V4 Pro
4+ week, 1+ day ago (203+ words) 0813 is a 1.6T Mixture-of-Experts model with 49B active parameters, built for advanced coding, tool use, and long-horizon agentic work. DeepSeek-V4-Pro-0813 is the official DeepSeek V4 Pro release, replacing the preview with substantially enhanced agentic capabilities and stronger production performance. It is available…...
Bionic Changelog • 1.0.8
3+ week, 6+ day ago (107+ words) LM Studio 1.0.8 - Release Notes#108---release-notes - Skills onboarding affordance under the chat input box. - Create Skill onboarding now invokes the skill in new chats. - Fixed composer suggestions clipping behind tabs or while scrolling. - Fixed composer suggestions not loading in the launchpad....
crunch3r/ai-toolbox • LM Studio Hub
3+ week, 5+ day ago (388+ words) 130 unique tools across 24 categories, fully integrated and ready for use. All tools dynamically registered with category-level gating. All tools registered via direct SDK pattern (no gateway indirection). Local Operations (isomorphic-git): git_status · git_diff · git_commit · git_log · git_add · git_checkout · git_stash · git_blame Remote API (GitHub CLI gh): gh_create_issue · gh_list_issues · gh_view_comments · gh_create_pr · gh_list_prs · gh_push Note: Remote operations require the…...
zexigh/kwikines • LM Studio Hub
3+ week, 1+ day ago (44+ words) 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…...
arminretro • LM Studio Hub
5+ day, 22+ hour ago (78+ words) arminretro lmstudio.ai DeepSeek V4 Flash is a Mixture-of-Experts model designed for efficient reasoning, coding, and agentic workflows Qwen Coder Next is an 80B MoE with 3B active parameters designed for coding agents and local development. Excels at long-horizon reasoning, complex tool usage,…...