Local AI Coding Hub: Run Claude Models Offline in 2026

Let ChatGPT, Claude, Cursor & any MCP client actually use your Mac — read & reply to email, manage your calendar, text over iMessage, find files, work with Teams, Slack & Office. On your Mac, no API keys, free.

Oracle: standalone multichain agent control plane with an optional encrypted, loopback-only self-hosted signer.

A real design engine for your AI agent: generate designs and print-ready PDFs, over MCP.

MCP server for Google Ads, Meta Ads & GA4 — works with ChatGPT, Claude, Cursor, n8n, Windsurf & more. 250+ tools for campaign management, analytics & optimization.

Extentos MCP server — deterministic tools for building smart-glasses apps with AI agents.

Claude Code plugin that offloads large outputs to filesystem and retrieves when required.

Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL visualization. LongMemEval R@5=97.45%. Self-hosted, Ollama-optional

Compatibility package for Correctover runtime security. The legacy standalone MCP server has been replaced by correctover-mcp-gateway; the runtime SDK is available as correctover.

An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive interface for managing, testing, and using MCP servers with your favorite chat plugins.

Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

Agent Smith has taken over your terminal: he recursively breaks down tasks and mercilessly executes them with Claude Code CLI/Opencode/openclaw until your project is "assimilated." Red pill or blue pill? On GitHub, only cloning his code matters.

See AI thinking in real time — 3D orb that visualizes Claude Code reasoning. Free, open-source MCP server

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

DSH 官方公众号收录的 TUI 补位插件：Claude Code 风，鲸鱼顶栏/实时状态/流式思考/双击 Esc 回滚/上下文进度+TPS。npm 一键装。 DSH official WeChat featured TUI plugin — Claude Code style: whale bar, live status, streaming thoughts, double-Esc rollback, context bar + TPS. npm one-click.

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.

A Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield. EN/ES.

Model Context Protocol for WinDbg.

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

Helping coding agents never make mistakes working with public or private libraries without wasting the context window.