multi-model

VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。

多模型同时对话、文生图，纯前端。Multi-model simultaneous chat、text-to-image generation, all done through pure front-end (API mode, no server-side needed).

Open-source, self-hosted platform to build, host, and chat with AI agents — LLM chat bots and image/video generation agents — from a single interface. Bring your own API keys.

A parallel AI window for Claude Code. Fork conversations to Gemini, GPT, DeepSeek, or any model via OpenRouter, then fold results back.

Multi-model deliberation skill for GitHub Copilot CLI

Multi-model AI pipeline for automated job hunting: web search → LLM triage → CV analysis → Telegram delivery

Turn Codex or Claude Code into a coordinated team that plans, completes, checks, and documents project work.

本地多模型路由器：让 Codex 桌面端 / Claude Code / 任意 OpenAI 客户端在一个菜单里共用 GPT、DeepSeek、Kimi、GLM、Gemini、Claude、ChatGPT 订阅额度 | Local multi-model router: one menu for GPT + any OpenAI-compatible model, with Claude/Gemini/ChatGPT subscription pools,纯文本模型视觉中继借眼看图

Model router for AI coding agents: installs routing rules, 8 subagents, hooks and a CLI runner so your AI picks model and effort per task and saves tokens

Interactive multi-agent collaboration, meetings, group chats, and task execution for DeepSeek Harness.

CLI-first multi-model orchestrator — routes tasks to Codex, Gemini, and Claude

Multi-model AI debate for your entire project lifecycle. Plans, specs, research, and code. Free and open source.

One question in, four AIs debate it, one verdict out. Gemini, Perplexity, ChatGPT, and Claude - with accounts, debate history, and a spend-capped free tier.

Multi-model AI council — spawn Claude, GPT, Gemini, and Grok as parallel coding agents to get independent opinions. CLI + pi extension.

Stress-test your decisions with adversarial AI debate. MCP server for Claude Code. Skeptic vs Steelman, web-search grounded, confirmation bias attack.

Coordinate Codex/GPT, Kimi Code, and Grok from one installable Codex plugin.

Route each Claude Code task to the cheapest Claude model tier that can do it well — via model-pinned subagents.

A blind panel of models + a judge, for decisions where being wrong is expensive. Verifies before it synthesizes; counts consensus by model family, not by head.

Orchestrates a tiered team of AI coding agents on opencode, under hard budgets.

An open advisory communication channel for delegated AI workers — when a worker from other provider than Claude gets stuck, it escalates a curated problem to a stronger model of choice for a read-only second opinion.