install-llm-council
LLM Council — multi-model consensus app with one-command setup. Ask one question to many models, let them critique each other, get a synthesized chairman answer. OpenRouter/OpenClaw-native backend + React/Vite frontend. Zero config — credentials resolve automatically.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- install-llm-council
- version
- 1.1.6
- metadata
- { "repo": "https://github.com/jeadland/llm-council", "tags": [ "llm", "openrouter", "openclaw", "install", "vite", "fastapi", "consensus", "multi-model" ], "category": "devtools" }
- description
- LLM Council — multi-model consensus app with one-command setup. Ask one question to many models, let them critique each other, get a synthesized chairman answer. OpenRouter/OpenClaw-native backend + React/Vite frontend. Zero config — credentials resolve automatically.
- slash_command
- /install-llm-council
03 SKILL.md 正文
LLM Council (with Installer)
LLM Council — ask one question to many models, let them critique each other, get a synthesized chairman answer.
This skill is the fastest way to run it: one command installs dependencies, configures credentials, and launches both backend and frontend. No manual setup, no API key prompts.
OpenClaw-native: Credentials resolve automatically from OpenClaw config or workspace .env. Falls back to the local OpenClaw gateway (port 18789) if no OpenRouter key is found.
Two Ways to Use LLM Council
| Mode | Best For | Command |
|---|---|---|
| Quick answer | Fast decisions, mobile, casual questions | /council "Your question" (requires ask-council skill) |
| Full discussion | Deep research, exploring disagreements, seeing all model responses | /install-llm-council then open browser at :5173 |
Slash Command
/install-llm-council [--mode auto|dev|preview] [--dir PATH]
When the user says /install-llm-council, run:
bash ~/.openclaw/skills/install-llm-council/install.sh
The script will:
- Resolve credentials — env var → workspace
.env→ OpenClaw local gateway (no prompt ever) - Clone or pull
https://github.com/jeadland/llm-councilto~/workspace/llm-council uv sync— Python backend dependenciesnpm ci— frontend dependencies- Write
.env— API key/URL for OpenRouter direct or OpenClaw gateway mode - Start app — uses hardened
start.shwith mode-aware startup and health checks - Auto-handle port conflicts — selects safe fallback ports when defaults are busy
- Print practical access URLs — Caddy route and common direct fallbacks
Flags
| Flag | Default | Description |
|---|---|---|
--mode auto |
auto |
Detect Caddy on :5173 and prefer preview mode; otherwise dev mode |
--mode dev |
— | Run Vite dev server (hot reload, port 5173 default) |
--mode preview |
— | Build + run Vite preview (port 4173 default) |
--dir PATH |
~/workspace/llm-council |
Override clone directory |
Credential Resolution (OpenClaw-native)
The installer never prompts for API keys. It resolves credentials in this order:
- Environment —
OPENROUTER_API_KEYalready exported - Workspace
.env—~/.openclaw/workspace/.envcontainsOPENROUTER_API_KEY=... - OpenClaw gateway — reads
~/.openclaw/openclaw.json→gateway.auth.token+gateway.port- Sets
OPENROUTER_API_URL=http://127.0.0.1:<port>/v1/chat/completionsin.env - Uses the gateway token as the bearer key (OpenAI-compatible endpoint)
- Sets
Ports
| Service | Port | Notes |
|---|---|---|
| Backend (FastAPI) | 8001 | Always |
| Frontend dev | 5173 | --mode dev (default) |
| Frontend preview | 4173 | --mode preview |
Files
| File | Purpose |
|---|---|
SKILL.md |
This file — skill documentation |
install.sh |
Main one-shot installer/launcher |
stop.sh |
Stop background services |
status.sh |
Check if services are running |
pids |
Saved PIDs for background processes |
Agent Instructions
When user says /install-llm-council or "install llm-council" or "start llm council":
bash ~/.openclaw/skills/install-llm-council/install.sh
Report back the access URL from the script output (e.g. http://10.0.1.X:5173).
To stop:
bash ~/.openclaw/skills/install-llm-council/stop.sh
To check status:
bash ~/.openclaw/skills/install-llm-council/status.sh
Example Output
✅ LLM Council installed and running!
Mode: dev
API: openrouter
Backend: http://127.0.0.1:8001
Frontend: http://10.0.1.42:5173
Stop: bash ~/.openclaw/skills/install-llm-council/stop.sh
Status: bash ~/.openclaw/skills/install-llm-council/status.sh
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.