antonbabenko/deliberation — GitHub trending stats & insights

antonbabenko/deliberation

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.

Visit GitHub

JavaScript

154

7 contributors

MIT License

Social mentions

Recent discussions about this repository across the web

When a hard coding decision needs a second opinion, don’t settle for one model. Deliberation is an MCP server and Claude Code plugin for getting second opinions from GPT, Gemini, Grok, and OpenRouter…

@DanKornas · x.com

"Panels of models which consistently outperforms individual models" - this is exactly the point I was chasing when working on the Deliberation. Ask Codex, Gemini, Grok, and 400+ OpenRouter models…

@antonbabenko · x.com

🤖 deliberation ⭐ 59 stars Stop trusting a single LLM. Make Gemini, Grok, and DeepSeek debate your code inside Cursor to find bugs and reach consensus before you commit. 🔗 🌐 #AI #MachineLearning

@Marco_Ramilli · x.com

Most agent demos hide the hard parts. This one is more interesting because it touches the actual Claude Code workflow. Ask Codex, Gemini/Antigravity, Grok (xAI), and 300+ more models through…

@AIDailyGems · x.com

Run this beside your current assistant for one repo and compare diff quality, not vibes. Ask Codex, Gemini/Antigravity, Grok (xAI), and 300+ more models through OpenRouter including Qwen, Kimi,…

@AIDailyGems · x.com

Updated v1.16.0 ( ): `/consensus` is now a 3-stage loop. Stage 2 adds a blind cross-review where each external rates the others' answers, anonymized, before Claude adjudicates. Pattern from…

@antonbabenko · x.com

🤖 claude-delegator ⭐ 26 stars Why trust just one LLM? Bring Gemini, Grok, and Codex into Claude Code for arbitrated consensus and multi-expert reviews on your codebase. 🔗 #AI #MachineLearning

@Marco_Ramilli · x.com

Social mentions

Repository activities