A harness for every question. A panel of 15 frontier models that writes its own playbook per question — fan out, debate to convergence, cross-examine under adversarial review, or run a tournament — and checks its work before it reaches you.
AI Consultants convenes a panel of up to 15 frontier models — each with a distinct persona — and, crucially, decides how they should deliberate for the question in front of them. It classifies the question, picks an orchestration shape, and iterates until the answers converge: the way a workflow builds a harness for the task at hand.
Simple questions get a quick read. Hard ones loop through debate until the panel converges. Security questions are stress-tested by an adversarial gate that tries to refute the leading answer. “Which approach?” runs a tournament and crowns a winner. The process fits the problem — it isn’t hardcoded.
The result: one recommendation that survived scrutiny, with the points of agreement, the dissent, and the path it took to get there all on the table.
Built for developers who want more than a single opinion.
Gemini, Codex, Mistral, Kilo, Cursor, Aider, Amp, Kimi, Claude, Qwen3, GLM, Grok, DeepSeek, MiniMax, and Ollama. Each with a unique persona.
All responses are combined into a single weighted recommendation with confidence scoring and consensus analysis.
Consultants critique each other across multiple rounds. Positions evolve. Anonymous peer review identifies the strongest arguments.
Questions are classified by category and routed to the most relevant consultants. Security questions go to security experts first.
Premium, standard, and economy model tiers. Choose max_quality for critical decisions or fast for quick checks.
Budget enforcement, semantic caching, cost-aware routing, and response limits. Stay within budget without sacrificing quality.
Share large files without burning the consultants' context window. AST-based skeleton extraction, category-aware project tree, and PRIMARY/CONTEXT relevance tags let you point the panel at what matters.
A planner picks how the panel deliberates per question — a convergence loop that iterates until answers agree, an adversarial refutation gate for security, a tournament to pick one winner, or an exhaustive sweep. Not a fixed script.
The panel calibrates itself. An uncorrelated-value audit flags consultants that only echo the others, while blind peer-review and pairwise-judge Elo derive each model's intelligence, taste, and cost from real runs — not hand-tuned guesses.
Your question is categorized — architecture, security, performance, code review — and scored for complexity and intent. From that, the planner picks an orchestration shape: how the panel should deliberate this specific question.
The relevant consultants are queried in parallel. Each returns a structured response — summary, analysis, pros/cons, and a 1–10 confidence score — from its own persona and focus area.
The chosen shape takes over. Converge loops debate rounds until the panel agrees (not a fixed count). Adversarial sends the leading answer through a refutation gate. Tournament pits approaches head-to-head. Exhaustive keeps probing until no new angle appears.
Consensus is scored, confidence intervals computed, and one weighted recommendation is produced — with the dissent and the convergence path it took, so you see not just the answer but how much to trust it.
Each consultant has a distinct persona that shapes their analysis. The invoking agent is automatically excluded to prevent self-consultation.
# Run directly — no install needed npx ai-consultants "How should I structure my auth system?" # With a preset npx ai-consultants --preset balanced "Redis or Memcached?" # Let the doctor recommend a preset for you (v2.13) npx ai-consultants doctor --suggest-preset --question "How can I prevent SQL injection?" # Scaffold persistent config at ~/.config/ai-consultants/ (v2.12) npx ai-consultants init # Run diagnostics npx ai-consultants doctor --fix # Install slash commands for Claude Code npx ai-consultants install # Keep the consultant CLIs up to date (v2.21) npx ai-consultants update-clis
# Install the skill curl -fsSL https://raw.githubusercontent.com/matteoscurati/ai-consultants/main/scripts/install.sh | bash # Ask your first question /ai-consultants:consult "How should I structure my auth system?"
# Clone and set up git clone https://github.com/matteoscurati/ai-consultants.git cd ai-consultants ./scripts/doctor.sh --fix # Run a consultation ./scripts/consult_all.sh "How should I structure my auth system?"
| Preset | Consultants | Use Case |
|---|---|---|
| minimal | 2 (Gemini + Codex) | Fast, cheap |
| fast | 2 + economy models, no debate | Quick checks |
| balanced | 4 (Gemini, Codex, Mistral, Kilo) | Standard consultations [default] |
| medium | 4 + standard models + light debate | General questions |
| thorough | 5 (+ Cursor) | Comprehensive analysis |
| cost-capped | Budget-conscious options | Minimal API costs |
| security | Security-focused + debate | Security reviews |
| high-stakes | All + debate | Maximum rigor for critical decisions |
| max_quality | All + premium models + debate + reflection | Critical decisions |
| local | Ollama only | Full privacy, no API calls |
| Strategy | Description |
|---|---|
| majority | Most common answer wins (default) |
| risk_averse | Weight conservative responses higher |
| security_first | Prioritize security considerations |
| cost_capped | Prefer simpler, cheaper solutions |
| compare_only | No recommendation, just comparison |
# Core features ENABLE_DEBATE=true # Multi-agent debate ENABLE_SYNTHESIS=true # Automatic synthesis ENABLE_SMART_ROUTING=true # Intelligent consultant selection ENABLE_PANIC_MODE=auto # Automatic rigor for uncertainty ENABLE_STANCE_CONSENSUS=true # Exact-match stance consensus (v2.21, opt-in) # Defaults DEFAULT_PRESET=balanced DEFAULT_STRATEGY=majority # Ollama (local models) ENABLE_OLLAMA=true OLLAMA_MODEL=hf.co/prithivMLmods/VibeThinker-3B-GGUF # Cost management MAX_SESSION_COST=1.00 # Budget limit in USD WARN_AT_COST=0.50