Check Antigravity account quotas for Claude and Gemini models.

Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

Keep your Claude access token fresh 24/7.

Council Chamber orchestration with Memory Bridge.

Remove AI-generated jargon and restore human voice to text.

Gemini CLI for one-shot Q&A, summaries, and generation.

Build and run Gemini 2.5 Computer Use browser-control agents with Playwright.

Perform complex, long-running research tasks using Gemini Deep Research Agent.

Transcribe audio files using Google's Gemini API or Vertex AI.

Orchestrate multi-LLM councils to produce and merge implementation plans.

Equips agents to search for and offload tasks to local models in LM Studio.

Monitor Minimax Coding Plan usage to stay within API limits.

A comprehensive AI model routing system that automatically selects the optimal model for any task.

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image).

Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq).

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Text-to-speech via OpenAI Audio Speech API.

Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).

Use the @steipete/oracle CLI to bundle a prompt plus the right files.

Search the web with AI-powered answers via Perplexity API.

Transform into 31 specialized AI personalities on demand.

Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent.

Turn recipes into a Todoist Shopping list.

Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens.

Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).

Search X/Twitter in real-time using Grok. Find tweets, trends, and discussions with citations.

Captures learnings, errors, and corrections to enable continuous improvement.

Generate contextual follow-up suggestions after AI responses.

Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.

Create and manage AI agent tasks via Manus API.

Switch between Claude, Codex, and Gemini when one gets stuck.

Multi-perspective feedback from spawned sub-agent personas.

Debate decisions from multiple worldviews to expose blind spots.

AI alignment exploration through conflicting optimization targets.

Generate bash scripts for AI agent loops (Codex, Claude, OpenCode).

Manage autonomous AI research agents with SQLite tracking.

Run Claude Code as a skill, control from WhatsApp.

Adversarial analysis to critique, fix, and consolidate solutions.