— · no license
Claude Code plugins that explore the possibilities of autonomy and self-guided behavior for coding agents
v0.12.0 · MIT
Point it at your coding-agent session traces (Claude Code, Codex, OpenCode, Gemini, Pi, …) and get failure-mode + efficiency findings. CLI + SDK over the @tangle-network/agent-eval analyst suite — observe live sessions, run your own analysts, redact, and
v0.6.82 · MIT
Local-first coding agent memory for Claude Code and OpenAI Codex
v1.0.0 · MIT
iOS/SwiftUI test automation & accessibility skill for Claude Code. Visual testing using computer use, memory leak analysis, and adding accessibility identifiers.
— · GPL-3.0
Run multiple Claude Code accounts as one. Auto-switches on rate limits and resumes your session no lost context, no logout dance.
v1.3.0 · MIT
The ultimate Claude Code toolkit for Unity — 20 AI agents, 22 slash commands, 41 skills, and safety hooks for AI-assisted Unity game development. Drop-in, production-ready.
— · no license
Governance standard and reference toolset for LLM-maintained knowledge corpora
v1.0.0 · MIT
The agent harness for offsec. It's a plugin for Claude Code packed with skills, hooks, memory system that works best for using Claude Code to achieve autonomous pentest/ctf
v0.52.55 · AGPL-3.0-only
Installer for the Wizard-AI environment: AI CLI tools and Claude Code skills (graphify, llmlingua, flashrank, markitdown and more). Clones the repo and runs the platform setup script.
v1.1.12 · MIT
Trusty Squire gives coding agents the ability to provision, ship, and pay — without your keys or card ever leaving the vault.
— · Apache-2.0
Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite store.
v1.81.9 · MIT
Kolbo AI MCP Server - Generate images, videos, music, speech, and sound effects from Claude Code
v0.4.3 · MIT
Switch between multiple Claude Code accounts instantly, in-session, no browser required. CLI + Claude Code commands + optional auto-stop-at-threshold hook.
v0.46.1 · MIT
Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback.
— · no license
Local AI Coding Hub: Run Claude Models Offline in 2026
— · MIT
Claude Code 的記憶系統 | A memory system built with hooks + markdown. Zero dependencies.
v1.69.2 · MIT
PTY session management, WebSocket streaming, and REST API server for Claude Code conversations
v0.11.60 · MIT
Extentos MCP server — deterministic tools for building smart-glasses apps with AI agents.
— · MIT
Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).
— · no license
Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.
— · no license
Claude Code plugin that offloads large outputs to filesystem and retrieves when required.
— · no license
Claude Code plugin — code quality hooks, knowledge graph, impact-aware reviews, decomposition enforcement. Babysitter for your AI's code quality.
— · MIT
Autonomous session memory for Claude Code. Never lose context, never repeat yourself. AI-powered summaries, searchable history, and automatic context injection. 📦 npm install -g memctx
— · MIT
Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.