Surface AI blindspots before you ship. Put up to 8 AI models on every research, design or coding task.
18 AI personas deliberate your hardest decisions across multiple LLM providers. Aristotle, Feynman, Kahneman, Torvalds & more — structured multi-round deliberation with genuine model diversity. One command: /council
Web app for teams of 20+ members. In-built connections to major LLMs via API. Share chats, prompts, and agents in team or private folders. Modern, fully responsive stack (Next.js, Node.js). Deploy your own vibe-coded AI apps, agents, or workflows—or use ready-made solutions from the library.
AI-powered real estate platform with conversational property search, analytics, and market insights. Built with FastAPI + Next.js + ChromaDB.
Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tier memory, Agent Packs marketplace, zero telemetry. Python 3.12+, Apache 2.0.
MVP of an idea using multiple local LLM models to simulate and play D&D
Open-Source Library for Fully Cooperative Multi-LLM Reinforcement Learning
鸣弦/MIXIA Framework (formerly persona-vault) — 人与AI协作的团队操作系统
BMO - Local Ai companion
Recursive agent orchestration with multi-LLM consensus
Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Cursor, or Gemini from any compatible tool.
The most powerful open-source TradingView AI agent. 50 tools, 15 models (Claude, GPT, Gemini, Qwen, DeepSeek, MiniMax), Pine Script v6, quant/HFT/hedge fund skills.
[ARCHIVED] 已迁移到 MIXIA-Framework repo
A visual layer for AI agent orchestration. Independent analysis, structured synthesis. Local or cloud LLMs.
Production-grade memory operating system for agentic AI. Interoperates with every major framework via MCP, OpenAI-compatible gateway, and native /v1/* REST — Claude Code, OpenClaw, ZeroClaw, Hermes, MemPalace, LangChain, LlamaIndex, CrewAI, AutoGen, Mem0, Letta, Zep. In production use since December 2025. Apache 2.0.
Local, BYOK code review for any language. No SaaS, no telemetry.
Three LLMs review your design plan in parallel — paste 30 lines into your CLAUDE.md, no install needed.
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface
ModelArena: A Competitive Environment for Multi-Agent Training
Add a description, image, and links to the multi-llm topic page so that developers can more easily learn about it.
To associate your repository with the multi-llm topic, visit your repo's landing page and select "manage topics."