
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
Explore trending open-source projects primarily written in Shell.
43 Shell repositories

A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.
An unofficial, experimental suite of AI Skills that reconstructs design principles from Mino's public materials into repeatable, evidence-based decision workflows.
An automated GitHub Actions workflow that continuously monitors multiple source repositories, builds consistently signed release APKs with deterministic versioning, and supports scheduled, manual, and event-driven triggers.
Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.
Open-source Agent Skill that drives the BaoCut macOS app CLI (transcribe · subtitle · translate · cut) from Claude Code, Codex, and other agents
A self-hosted, OpenAI-compatible LLM API gateway that runs on your own infrastructure with multi-credential pooling, hot-reloading, and secure HTTPS exposure via Cloudflare Tunnel without opening any inbound ports.
Automates Android APK patching from analysis to deployment through a multi-agent AI pipeline, with model-agnostic prompts and steering context usable across any AI coding assistant.

A transparent Claude Code plugin that augments session continuity through state capture, recovery guidance, and skill recall, surpassing Codex CLI parity without replacing the native compaction algorithm.

An always-on token efficiency skill for coding agents that reduces bills by ~31% and output by up to 81% without sacrificing correctness.

A centralized repository for personal AI agent rules and best practices with one-command installation via curl.
ENCORE simplifies running Ableton Live 12 Suite on Linux with a single guided command that handles Wine patching, HiDPI, audio, and VST3 integration.

A read-only Codex Desktop skill that audits telemetry and tool surfaces to keep long-running workflows scoped and efficient.

A curated library of 51 production-ready specialist subagents for Gemini CLI that can be dropped in and automatically delegated to.

A unified module that bundles TEESimulator-RS and PlayIntegrityFork to achieve and automatically maintain STRONG Play Integrity with one flash, no manual keybox or fingerprint hunting.
Turn a raw idea into precise, build-ready docs by running it through 13 expert personas that grill and challenge it until every decision is locked, so your AI can execute autonomously without vague prompting.
Integrates Kafka, PySpark, HDFS, Hive, Elasticsearch, FastAPI, and Vue to enable real-time ingestion, processing, storage, retrieval, and visualization of live financial data for commodities like gold, silver, crude oil, and copper.

Skills and hooks for Claude Code that reduce token waste by steering the model and enforcing rules, without running in the request path.

A command hook that blocks risky shell commands for coding agents like Claude Code, Codex CLI, and Devin CLI.