108 boosters for "local" — open source, verified from GitHub, ready to install
A local SQLite-based command-line task board for AI agents and developers to manage multi-step coding tasks, track progress, and coordinate work across sessions without external dependencies. Ideal for breaking down complex implementations into trackable subtasks with comments and checklists.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Dinox MCP Server enables Claude to understand images through advanced object detection, localization, and captioning by connecting to the DINO-X vision model. Developers building multimodal AI applications benefit from seamless integration of real-world visual perception into LLM workflows.
"name": "prism-mcp-server", "mcpName": "io.github.dcostenco/prism-mcp", "description": "The Mind Palace for AI Agents — persistent memory (SQLite/Supabase), behavioral learning & IDE rules sync, multimodal VLM image captioning, pluggable LLM providers (OpenAI/Anthropic/Gemini/Ollama), OpenTelemetry
"name": "claude-seo-assistant", "description": "权威性 SEO 助手工具，支持 Next.js 项目的元数据优化、结构化数据、内容审计、客座博客搜索、站外 SEO 和本地 SEO 分析", "author": "Claude Code SEO Team",
Librarian is a local-first documentation CLI that indexes and retrieves docs using vector embeddings and SQLite, enabling developers to search and manage documentation offline with AI assistance.
Automates PR auditing, merging to main, and local environment synchronization, helping teams enforce code quality gates and streamline integration workflows.
Skill Forge automates the creation and packaging of reusable AI skills by intelligently detecting, fetching, and organizing resources from GitHub, documentation, or local directories. Developers and AI engineers benefit from streamlined skill development workflows and reduced manual configuration overhead.
Run CI checks locally, mirroring the GitHub Actions workflow in . Assume all tools (stack, coqc, coq_makefile) are already installed — no Docker or opam setup needed. Do NOT use (that's only for CI containers). All commands must be run from the workspace root using relative paths. The argument is:
Persistent local memory for AI agents. Save, recall, and search project decisions as local JSON. Zero cloud, zero infrastructure.
An MCP server that enables Claude to maintain persistent long-term and short-term memory across conversations using a local SQLite database. Developers and AI agents benefit from enhanced context retention and conversation continuity.
"description": "Shared development tools for Submariner repositories", "name": "Submariner Contributors", "url": "https://github.com/submariner-io"
Syncs OpenClaw framework, ClawHub, and Skills documentation into a local searchable mirror for the QMD memory backend, enabling AI agents to access fresh, precise references during coding tasks.
"name": "codebase-context", "description": "Pre-maps your codebase architecture, conventions, and team memory so AI agents navigate with precision instead of exploring. Local-first MCP server with AST-backed hybrid search.", "main": "./dist/lib.js",
"name": "claude-context-optimizer", "description": "ContextShield, CLAUDE.md analyzer, interactive dashboard, confidence learning, and token optimization for Claude Code", "name": "Egor Fedorov"
Skill Forge automates the creation and packaging of AI skills from external sources like GitHub repos and documentation, enabling developers to quickly convert existing resources into reusable Claude Code skills. It's ideal for developers who want to streamline skill development and integrate external knowledge bases into their AI workflows.
"name": "open-plan-annotator", "description": "Interactive plan annotation UI: review, strikethrough, and comment on Claude's plans before approving. Fully local, no external services.", "homepage": "https://github.com/ndom91/open-plan-annotator",
Local MCP server for eBay APIs - provides access to eBay developer functionality through MCP (Model Context Protocol)
Use when organizing media files (movies, TV, anime) on NAS or local storage - cleaning junk files, merging scattered episodes, normalizing folder names to "Title (Year)" format, and verifying episode completeness against TMDB
CortexGraph is a temporal memory system for AI assistants that implements human-like forgetting curves using local storage (JSONL and Markdown), enabling natural conversation memory across Claude, Cursor, and other platforms without explicit save commands.
MCP server that enables previewing local HTML files and capturing screenshots within Claude, streamlining web development workflows by allowing developers to test and visualize HTML changes without leaving their AI assistant.
"name": "autonomous-agent", "version": "7.19.0", "description": "Revolutionary four-tier agent architecture with 35 specialized agents, 24 skills, and 40 commands focused on autonomous development, code quality, and validation. Strategic Analysis & Intelligence (Group 1) analyzes and recommends, Dec
This sub-skill generates a complete email marketing strategy tailored to your business type, including: Invoked by from the main email skill. First, check if exists and contains business type. If not, analyze context signals:
RagCode MCP is a semantic code navigation tool that integrates RAG-powered code search into Windsurf and other IDEs, enabling developers to intelligently query and understand multi-language codebases using local LLMs. It's ideal for developers working with Laravel, Go, Python, and PHP who need fast, context-aware code exploration without leaving their IDE.
