AI/ML●●Solid
AI agents debating questions that stump LLMs
AI agents debate instead of refusing — fun to test with paradoxes and predictions.
Rabbit HoleCrowd Pleaser
ttlcc13
302mo ago
Back to browse
GitHub Repository
Run a council of local LLMs that debate, critique, and synthesize — no API keys needed.
73 starsPython
Run an Agent Council of LLMs that debate and synthesize answers
by JitseLambrichts·Mar 12, 2026·8 points·2 comments
AI Analysis
●●SolidBig BrainNiche Gem
Agent council debate architecture with GSM8K benchmarks showing accuracy gains.
Strengths
- •Dual architectures: sequential Planning/Execute/Critique and parallel expert councils.
- •Zero-config auto-discovery of Ollama and LM Studio endpoints, no .env setup.
- •Assigns distinct models to different reasoning stages for optimized performance.
Weaknesses
- •Multi-agent local LLM orchestration is becoming a crowded category.
- •Accuracy gains on GSM8K may not translate to real-world reasoning tasks.
Category
Target Audience
Developers running local LLMs who want multi-agent reasoning
Similar To
LangGraph · AutoGen · CrewAI
Post Description
I built a local-first UI that adds two reasoning architectures on top of small models like Qwen, Llama and Mistral: a sequential Thinking Pipeline (Plan → Execute → Critique) and a parallel Agent Council where multiple expert models debate in parallel and a Judge synthesizes the best answer. No API keys, zero .env setup — just pip install multimind. Benchmark on GSM8K shows measurable accuracy gains vs. single-model inference.
Similar Projects
AI/ML●●Solid
I built AI agents that debate questions LLMs usually refuse to answer
AI agents debate outcomes in a Manifold Markets-style prediction interface.
SlickBig BrainShip It
ttlcc13
102mo ago
AI/ML●●Solid
Fixy – Real-time group chat with humans and AI agents (GPT, Claude,..)
AI agents debate each other in real-time before synthesizing one final answer.
SlickBig BrainSolve My Problem
frdfrd
102mo ago
AI/ML●Mid
AI Council Debate
The five-role council (Analyst, Muse, Logician, Ethicist, Pragmatist) is a neat way to force diversity of perspective and makes for entertaining, shareable threads; live chat, voting and a verdict mechanic add community glue. It feels like a well-polished demo rather than a research advance — interesting and fun, but derivative of existing multi-agent/LLM playgrounds and likely limited by shallow or repetitive model outputs unless they invest in moderation, grounding, or stronger agent orchestration.
Crowd PleaserShip It
smakosh
313mo ago
AI/ML●●Solid
Agent Council – Claude, Codex and Gemini debate code and engg questions
CLI agents with repo access debate, not just API calls.
Big BrainNiche Gem
yogirk1
102mo ago
AI/ML●●Solid
DocForge – Multi-Agent RAG That Fact-Checks Its Own Answers
Multi-agent fact-checking loop, but RAG hallucination fixes are table stakes now.
Big BrainShip It
toheed11
113mo ago