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

Unofficial community workarounds for Claude Code (empty thinking summaries; missing context-usage icon; no copy/paste of markdown).

🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.

Intelligent AI Gateway for IDEs & Agents — Semantic cache, Privacy Firewall, Infrastructure Command Center, and Autonomous Cost-Optimization.

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.

Connect coding agents to fast Inference.net models

One command to cut token usage by up to 50%+

An open canvas workspace for AI coding agents

Full-stack consulting skill for Claude Code — 6 AI agents, 16 strategy frameworks, CPA-level financial modeling, zero hallucinations

Playwright MCP server undetected by anti-bots and captchas: AI agent browses the web on anti-detect stealth Firefox, Python, undetected browser automation, scraping, computer use.

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Unbrowse — api native browser Skill/CLI/MCP/SDK for any agent. Auto-discovers APIs from browser traffic, generates skills on the fly to call APIs directly 100x faster, 80% cheaper locally.

Claude Code plugin: run the Antigravity CLI (Gemini) as a collaborating sub-agent with intelligent model routing across the SDLC. Community project; not affiliated with Google/Anthropic.

Command-line tool to customize your Claude Code theme colors, thinking verbs and more.

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.

Mechanical plan/dev/self-audit/external-audit gates for AI coding agents, with a configurable role-routing topology engine, an MCP-UI live status panel, and native-tooling Claude Code V2 dispatch. Claude Code, Codex, OpenClaw, and PyPI.

Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

Opinionated AI coding agent and dev environment automation for macOS

The practices that made software work didn't stop working. They stopped keeping up. PAAD brings them back at AI speed.

UiPath agent skills for Claude Code, Codex, Cursor, Copilot, Gemini and OpenCode — RPA, UI automation, UI testing, coded agents/apps/workflows, and troubleshooting. Distributed as the UiPath Claude Code plugin.

Persistent memory for Claude Code, Cursor and Codex. Facts are typed, sourced, and retired when they change. Local SQLite, no API keys.

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1