Lmstudio Python Packages

vmlx

vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Scheduler + Cont Batching + etc!

swival

A small, powerful, open-source CLI coding agent that works with open models.

cli-comet

Comet helps you save 15,000+ tokens! Comet is a TUI application that automatically generates descriptive git commit messages using local language models via Ollama or LMStudio or Openrouter. It analyzes your staged git diffs and provides a clean interface to review, edit, regenerate, and commit your changes instantly.

claude-codex-local

Local backend bridge for Claude Code, Codex, and Pi.

ownscribe

Local-first meeting transcription and summarization CLI

rikis

Lightweight agent that pulls and runs LLM benchmarks from Protorikis Bench

agent-smithers

An agentic AI assistant for the Matrix chat protocol using the Responses API

agentirc

Agentic IRC chatbot using the Responses API

docbt

Documentation Build Tool - Generate YAML documentation for dbt models with optional AI assistance. Built with Streamlit for an intuitive and familiar web interface.

semantic-qa-gen

A Python library for generating high-quality question-answer pairs from PDF, DOCX, MD, and TXT files

lazyllama

a smol tool for managing local models

devorch

Multi-provider AI coding assistant CLI with 13+ providers

agent-delegate

Universal cheap-subagent CLI — route low-reasoning tasks from Claude Code / Codex to Ollama, LM Studio, OpenRouter, Anthropic Haiku, and other backends.

laperf-power

La Perf is a framework for AI performance benchmarking — covering LLMs, VLMs, embeddings, with power-metrics collection.

laperf

Local AI Performance Benchmark Suite - Reproducible AI hardware benchmarks with real-time power monitoring