Concilium provides a multi-agent consultation framework that sends prompts to multiple LLM providers in parallel and synthesizes their responses. It includes three standalone servers wrapping OpenAI Codex CLI, Gemini CLI, and Qwen CLI, each with structured error detection and configurable fallback chains. The framework supports consensus-building workflows where disagreements between providers trigger follow-up iterations. Docker support and a Claude Code skill for triggering consultations are included.
Cognium trust score
83%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-19.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.