Fine-tune any Hugging Face model on your own laptop using QLoRA, then export to Ollama-ready GGUF.

LoRA/QLoRA fine-tuning assistant for Claude Code — data analysis, memory planning, hyperparameter recommendation, and training script generation

Deprecated npm distribution shim for backpropagate — prints install guidance for pipx/uv tool/pip. See https://github.com/mcp-tool-shop-org/backpropagate

Non-blocking background watcher for pi — start a process, SSH poll, or log tail and get pinged in-session on milestones, failure, or exit. Claude Code's Monitor tool, with conditional delivery.

Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles p

A powerful local and API-driven AI system assistant

Claude Code native autonomous ML research tool. Distributed as an npm package following GSD patterns.

Agent skill for managing LLM fine-tuning through Unsloth Studio API

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

MCP Server for Claude Code, Cursor, Cline, Copilot, Github Copilot, Windsurf - Visual AI Agent Plan Execution, Approval Workflow, Plan Visualization, Agent Orchestration. See what your AI is thinking before it writes code. Works with Claude, GPT, Gemini,

A Rust inference engine that runs a swarm of tiny specialist models that collaborate and learn continuously — on your GPU.

Embedding-based retrieval, hybrid scoring, RAG pipeline, and intelligence primitives for @forgrit/design-engine. Optional local LLM and ONNX runtime.