This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+4 more
Summary
AI summaryAdds a multi‑agent AI consultation framework with three MCP servers and fallback chains.
Full changelog
Claude Concilium v0.1.0
Multi-agent AI consultation framework for Claude Code via MCP.
What's Included
3 MCP Servers (standalone, plug & play):
mcp-openai— wraps Codex CLI (codex exec), OAuth auth, code review viacodex reviewmcp-gemini— wraps Gemini CLI (gemini -p), Google OAuth, 1000 req/day free, 1M token contextmcp-qwen— wraps Qwen CLI (qwen -p), DashScope auth, 3 model tiers
AI Concilium Skill — Claude Code skill for structured multi-agent consultation with fallback chains
Smoke Tests — MCP protocol verification without CLI tools installed
Features
- Parallel consultation with 2+ AI agents
- Production-grade fallback chains: OpenAI → Qwen → DeepSeek, Gemini → Qwen → DeepSeek
- Error detection (quota, auth, model availability)
- Proper timeout with SIGTERM/SIGKILL cleanup
- 10MB buffer limits for OOM protection
- Graceful shutdown handlers
Quick Start
git clone https://github.com/spyrae/claude-concilium.git
cd claude-concilium
cd servers/mcp-openai && npm install && cd ../..
cd servers/mcp-gemini && npm install && cd ../..
cd servers/mcp-qwen && npm install && cd ../..
node test/smoke-test.mjs
See README for full setup guide.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About spyrae/claude-concilium
Multi-agent AI consultation framework for Claude Code. Three MCP servers wrapping CLI tools (Codex, Gemini, Qwen) for parallel code review and problem-solving with fallback chains and error detection. Includes ready-to-use Claude Code skill.
Related context
Beta — feedback welcome: [email protected]