#multi-model

Evidence-grounded research agent for Claude Code & Codex: every claim gets a confidence rating + source-family tag, and adversarial gates block unsupported claims before they reach your report. Ships with a multi-model dispatcher.

Route bulk implementation to cheap executor LLMs (opencode/antigravity/cursor) with Claude as architect + judge - committed failing tests are the merge gate

Multi-Agent AI Orchestrator 2026 🚀 | YAML, 6+ LLM Providers, ReAct & Swarm

OpenAI- and Anthropic-compatible AI gateway. Capability-based routing. Streaming. BYOK passthrough. No key custody.

Claude Code marketplace for external model workflows: OpenAI Codex, Gemini CLI, and Google Antigravity.

异步跨模型 Goal Loop：Codex 规划验收，Claude 自主执行，10→20→40→80 分钟指数退避监测

Safe Codex orchestration with Grok execution, Claude review, and guarded quality gates

Unified LLM client — one interface for OpenAI, Anthropic, Gemini, Groq, DeepSeek. Parallel calls, vision support, cost tracking. Powers RawEval's multi-model evaluation pipeline.

A Claude Code skill that fans one hard question out to several frontier models (GPT-5.5, Gemini, Kimi, GLM) blind and in parallel, then has Opus 4.8 judge and synthesize one grounded answer. Multi-model test-time scaling with independence enforced and the judge kept separate from the panel.

All CLI Council for Claude Code — ask five models across four vendors the same hard question, let them rank each other anonymously, then decide yourself. Runs on the CLIs you already have. No API keys.

Multi-model, multi-agent OMP development workflow with Graphify