lm-studio — independent software & tools
-
apogee
Local-first terminal coding agent for any OpenAI-compatible endpoint — local or cloud. Full agentic tool loop, OS-enforced sandboxing (Landlock / seatbelt / Windows token), sessions, MCP, and A/B-measured mechanisms that make even small LLMs (4B–35B) deliver. Go + Bubble Tea.
-
Inferpal
Visual Studio 2022/2026 + VS Code extension: a local AI coding agent for Ollama, LM Studio or any OpenAI-compatible server. Agentic loop with 26 built-in tools — files, builds & tests, hybrid semantic code search, Git, web — inline ghost-text completions, MCP client & RAG, model bench & router. 100% local, no API key, no telemetry.
-
omm
Open source Model Manager - hardware-aware install and recommend for local LLMs (GGUF).
-
ModelTab
No-install BYOK AI chat PWA for OpenAI-compatible, Gemini, and local/LAN LLM endpoints.
-
AI-System-6
A Macintosh System 6 desktop where AI work stays visible. Local-first, model-agnostic, no framework.
-
ocds-procura-semantic-nexus
AI-Powered German Procurement Search Engine 2026 - OCDS Tender Matching & Company Profiles
-
daedalus-cli
Local-first AI coding CLI with embedded model router, multi-agent orchestration, and codebase indexing
-
lm-chat
Web frontend for LM Studio — browser access, adaptive memory, multi-user auth, MCP tools
-
fonos
A hotkey-first voice AI terminal for macOS & Linux: speak anywhere, transcribe, rewrite, capture notes/meetings, listen with TTS, and talk to AI agents using local or cloud models.
-
agentirc
Agentic IRC chatbot with multi-provider LLMs (OpenAI, xAI, LM Studio), tool use, MCP, and per-user history
-
mcp-ai-wpoos
NV Digital Open Operator System (NV oOS) is an Object-Oriented AI framework for WordPress connecting your data with OpenAI, Gemini, Anthropic, DeepSeek, Hugging Face, Cloudflare, OpenRouter & Ollama (Local) models. Create & manage AI Assistants that can interact with users, access WordPress (API) data, & perform as a MCP Server & Chat Agent
-
sir-thaddeus
Private, local-first AI assistant for Windows with permissioned tools, durable memory, and evidence-driven small-model improvements.
-
eckra
AI-powered Git management: smart commits, project stories, and the whole repo in one place
-
lilbee
The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both.