Tula is an open-source collection of OpenClaw skills, configurations, and patterns designed to transform a general-purpose AI agent into a personal health intelligence assistant.
-
Updated
Oct 17, 2026 - TypeScript
Tula is an open-source collection of OpenClaw skills, configurations, and patterns designed to transform a general-purpose AI agent into a personal health intelligence assistant.
Send hard, long-running work from Oh My Pi or pi to ChatGPT or Grok through the web app: context-rich repo archives, isolated browser auth, durable background jobs, and a saved answer that wakes the session that asked.
MCP server that wraps the xAI Grok CLI. Lets Claude Code, Cursor, Cline, and any MCP host use Grok as a peer code reviewer, adversary, and second-opinion consultant.
A cross-agent consultation bus: a CLI coding agent asks a different-provider agent for a second opinion — one advisor, or a multi-agent council that audits code and verifies every finding against its file:line. 12 agents: Claude, Codex, Gemini/agy, Grok, OpenCode, Hermes, Kimi, Cursor, Kilo, Cline, Goose, Pi.
A sidekick for you and your Pi agent: plain-language explanations, side questions, diagrams, PR review and second opinions, without cluttering the agent's context.
Reference implementation of Cross-Lab Adversarial Review (CLAR): run a rival-lab AI as an independent reviewer, then verify, reconcile, and escalate only the real disagreements.
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
Claude has friends. On the calls that matter it asks AIs from other families — Gemini, a fresh-eyes second Claude, optionally GPT — who catch the blind spots one model can't see alone.
Claude Code skill for cross-model review. One command packages files + prompt for ChatGPT Pro deep reasoning.
Claude Code plugin for second opinions: iterative adversarial debates between Claude and Codex over any subject, from specs, designs, and code to non-technical positions, ending in genuine agreement or a documented dispute.
Model-vs-model sparring skill for Claude Code, Codex, OpenCode and Cursor: a second opinion from Claude or Codex on a plan, architecture or code review, argued over several turns and folded into one answer.
Multi-model advisory board for Claude Code — get second opinions from Codex and Gemini
Claude Code plugin: Gemini 4 Argon reviews Claude's plans and commits with fresh eyes, gives second opinions, and takes delegated coding in an isolated git worktree.
Adversarial AI medical case-review board for Claude Code — blind specialist rounds, verified citations, dissent-preserving minutes, deterministic DICOM-to-3D. Not a medical device.
Cross-model adversarial review and idea generation for Claude Code. A Claude session orchestrates and ratifies; OpenAI (codex), Moonshot (kimi) and xAI (grok) seats probe, replicate and generate — all on subscription auth, no API key. Ten modes: review, forge, instrument audit, fragment verify, blind replication, and more.
Claude Code skill: hand code/plans to Codex (codex CLI) for an independent second-opinion review
Secure orchestrator for MRI second opinion. Clinician-in-the-loop workflow: Ingest -> QC -> AI Draft -> Mandatory Review -> Export. Features a state-machine API (TS), Python worker loops, and DICOM SR/FHIR support. Research Use Only (RUO). Designed for security, auditability, and verifiable AI-assisted diagnostic pipelines.
Multi-model second-opinion utility for structured deliberation in employee-agent workflows. Derived from llmcouncil; CLI-based providers.
Claude Code plugin: Gemini as second-opinion assistant (validator, challenger, researcher, summarizer subagents + auto-trigger hooks)
Bridge Claude Code and Codex on the same machine — second opinions, brainstorms, and direct MCP tool access between two AI coding agents.
To associate your repository with the second-opinion topic, visit your repo's landing page and select "manage topics."