gitwtfhub

wtf is multi-agent-deliberation?

juniper-tc02e/multi-agent-deliberation — explained in plain English

Analysis updated 2026-05-18

2PythonAudience · developerComplexity · 2/5LicenseSetup · easy

TL;DR

Four Claude Cowork and Claude Code skills that break a problem into sub tasks, debate it across diverse AI agent panels, judge by argument instead of vote, and synthesize one answer with a dissent record.

Mindmap

mindmap
  root((multi-agent-deliberation))
    What it does
      Dissect problem
      Debate with diverse agents
      Judge not vote
      Synthesize with dissent
    Tech stack
      Python
      Claude Code
      Claude Cowork
    Use cases
      High stakes decisions
      Design review
      Research grounded debate
    Audience
      Developers
      Power users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Get a hard question examined by multiple AI agents from different perspectives before trusting the answer.

REASON 2

Pick a compute tier that matches how important the decision is, from a quick quality boost to unlimited deliberation.

REASON 3

See a dissent register showing where agents disagreed instead of a single averaged answer.

REASON 4

Use the Max or Unrestricted tiers for high stakes research or design decisions.

What's in the stack?

PythonClaude CodeClaude Cowork

How it stacks up

juniper-tc02e/multi-agent-deliberation0-bingwu-0/live-interpreter010zx00x1/faresnipe
Stars222
LanguagePythonPythonPython
Setup difficultyeasymoderateeasy
Complexity2/52/52/5
Audiencedevelopergeneralgeneral

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · easy Time to first run · 5min
Free to use, modify, and distribute, including commercially, as long as you include the license notice.

Wtf does this do

Multi-Agent Deliberation is a set of four skills for Claude Cowork and Claude Code that let you get a question or problem examined by many AI agents working together instead of just one. Each skill breaks a problem down into smaller sub tasks, has a group of agents look at each sub task from different angles, has a separate judging step weigh their arguments instead of just counting votes, optionally challenges the conclusions to see if they hold up, and then combines everything into one final answer that also notes any disagreement along the way. The four skills, named General, Super, Max, and Unrestricted, differ mainly in how much computing effort they spend. General is meant as an everyday quality boost, using a handful of agents per sub task. Super and Max use more agents, more rounds of debate, and stricter judging, including using different AI models together rather than the same one repeated. Unrestricted has no limit at all and can keep working until it runs out of new ideas to check. The heavier tiers can spawn hundreds of agents, so picking the tier that actually fits the importance of the question matters, and each skill will tell you its plan and rough cost before it starts. The project explains that simply having several copies of the same AI model argue with each other is not automatically better, citing published research showing this can even do worse than a single model checking its own work multiple times. To avoid known problems such as debates drifting off topic, extra rounds adding cost without adding quality, and agents caving to whatever the majority says even when it is wrong, each tier builds in specific safeguards like enforcing genuinely different perspectives, stopping debates once they settle, and guarding against agents copying each other's conclusions instead of reasoning independently. Installing it in Cowork means downloading the plugin file from the releases page and uploading it. In Claude Code, you clone the repository and add it as a plugin, or build the installable bundle yourself with a provided script. No API keys, environment variables, or external services are needed. The project is released under the Apache 2.0 license.

Yoink these prompts

Prompt 1
Deliberate on whether we should rewrite this service in Rust or keep it in Go.
Prompt 2
/multi-agent-deliberation-super evaluate these three system design proposals and pick the strongest one.
Prompt 3
Run max deliberation on whether this security fix actually closes the vulnerability.
Prompt 4
Use unrestricted deliberation to stress test this business plan until no new objections come up.

Frequently asked questions

wtf is multi-agent-deliberation?

Four Claude Cowork and Claude Code skills that break a problem into sub tasks, debate it across diverse AI agent panels, judge by argument instead of vote, and synthesize one answer with a dissent record.

What language is multi-agent-deliberation written in?

Mainly Python. The stack also includes Python, Claude Code, Claude Cowork.

What license does multi-agent-deliberation use?

Free to use, modify, and distribute, including commercially, as long as you include the license notice.

How hard is multi-agent-deliberation to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is multi-agent-deliberation for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.