Search Packages

mlx-vlm

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

foundry-local-sdk

Foundry Local Manager Python SDK: Control-plane SDK for Foundry Local.

lilbee

Terminal-first local search and AI chat over your documents, code, and crawled websites. Semantic + hybrid search, vision OCR, auto-built wiki, browsable GGUF model catalog. Works as CLI, TUI, MCP server, REST API, or Python library. Offline by default, no sidecar services.

llm-autotune

Zero-config local LLM optimization for Ollama, LM Studio, and Apple Silicon MLX. Reduces TTFT by 40%, wall time for local agents by 46%, and RAM usage by 3x.

knowledge-rag

Drop docs, search instantly from Claude Code — 12 MCP tools, 20 format parsers, hybrid search + reranking. Zero servers, zero API keys, 100% local.

hey-cli-python

Your terminal buddy that turns plain English into shell scripts — and runs them. Powered by Ollama. 100% local, 100% private.

edgevox

Offline voice agent framework for robots.

foundry-local-sdk-winml

Foundry Local Manager Python SDK: Control-plane SDK for Foundry Local.

pullnexus

Pull-on-demand skill registry for local LLMs. Search, install, and contribute skills, tools, datasets, and playbooks for Ollama, LM Studio, and any local AI setup.

artifex

Small Language Model Inference, Fine-Tuning and Observability.

neurostack

Build, maintain, and search your knowledge vault. CLI + MCP server with stale note detection, semantic search, and neuroscience-grounded memory.

ollama-mcp-bridge

Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context Protocol) servers. Fully compatible, transparent, and developer-friendly, ideal for building powerful local LLM applications, AI agents, and custom chatbots

deepsleep-ai

Zero-cost background coding agent with layered memory, idle-time dreaming, MCP server, and Ollama support.

hellochusquis

Terminal AI agent with multi-provider fallback, file management, code execution, and persistent memory. Supports OpenRouter, Ollama, OpenAI, Anthropic, Gemini, Groq and 15+ more providers.

encoderfile

Python bindings for encoderfile.

mycoswarm

Distributed AI for everyone. Turn forgotten hardware into a thinking network.

lexaloud

A local, private Linux text-to-speech tool. Select text in any app, press a hotkey, hear it read by Kokoro-82M on your GPU.

velocirag

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

gitbriefly

Your daily developer standup — powered by your Git history

globalmm

Add vision to any local LLM, no training.

ltts

Quick CLI for local text-to-speech using Qwen3-TTS or Kokoro TTS.

locallens

Search your files by talking to them - 100% offline

grid-intelligence

GRID - Geometric Resonance Intelligence Driver: A comprehensive framework for exploring complex systems through geometric resonance patterns, cognitive decision support, local-first AI, and event-driven agentic systems

quaynor

Embed local models in your app