llm-council

Solid

Provider-agnostic multi-LLM deliberation. Three phases — independent responses, cross-model anonymized ranking, chairman synthesis. Provider config from env (OPENAI/ANTHROPIC/FIREWORKS/OPENROUTER/custom OpenAI-compatible base URL). Persists transcript to a wiki page when --wiki <slug> is passed. Use when the user wants multiple AI perspectives, consensus-building, or the "LLM Council" approach for high-stakes reviews, plan critique, or contested learning rules.

AI & Automation 2,296 stars 225 forks Updated 3 days ago

Install

View on GitHub

Quality Score: 86/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
0
Description 5%
100

Skill Content

# LLM Council Karpathy's LLM Council pattern, provider-agnostic. dair-academy's version hardcoded Fireworks; ours reads any OpenAI-compatible endpoint via env. ## When to use - High-stakes plan review (`/plan` crosses N-file threshold) - Conflicting learning-rules → re-resolve via vote - User invokes `/council "<query>"` or `/wiki council` - Architecture decisions where you want multiple viewpoints captured - Persisting deliberation as a wiki page for future reference ## Three phases 1. **Independent**: each model answers in parallel 2. **Ranking**: each model ranks anonymized peer responses 3. **Synthesis**: chairman model reads all responses + rankings → final answer ## Provider config Provider chosen via env. First-match wins: | Env var | Provider | Default base URL | |---------|----------|------------------| | `ANTHROPIC_API_KEY` | Anthropic | `https://api.anthropic.com` | | `OPENAI_API_KEY` | OpenAI | `https://api.openai.com/v1` | | `OPENROUTER_API_KEY` | OpenRouter | `https://openrouter.ai/api/v1` | | `FIREWORKS_API_KEY` | Fireworks | `https://api.fireworks.ai/inference/v1` | | `LLM_COUNCIL_BASE_URL` + `LLM_COUNCIL_API_KEY` | Custom OpenAI-compat | (user-supplied) | Override per-run with `--provider openai|anthropic|openrouter|fireworks|custom`. Default model rosters per provider live in `scripts/council.js` and can be overridden via `--models` CSV and `--chairman <id>`. ## Commands ``` node $SKILL_ROOT/scripts/council.js run "<query>" [--models id1,id2,id3]...

Details

Author
rohitg00
Repository
rohitg00/pro-workflow
Created
4 months ago
Last Updated
3 days ago
Language
JavaScript
License
None

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

council

5-model strategic advisory. Ask the same question to five different LLM seats in parallel, save each response to a persistent file, then synthesize a recommendation. Each seat is locked to a role (Theorist, Validator, Provocateur, Diagnostician, Field Engineer) so the responses disagree by design instead of converging by accident. Use when the user says "ask the council", "get opinions", "council on", "what do they all think", "multi-model opinion", or wants strategic input from multiple LLMs before making a decision.

0 Updated 6 days ago
eprouveze
AI & Automation Listed

llm-council

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

3 Updated 5 days ago
valorisa
AI & Automation Listed

llm-council

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

353 Updated today
aiskillstore