Roundtable
Fans out a question to multiple frontier models in parallel, optionally deliberates to consensus, and returns one decided answer from the command line or any MCP-capable coding harness.
README
<div align="center">
๐ช Roundtable
A council of frontier models โ for the decisions that matter.
One question โ many minds โ one decision.
Fan a question out to Grok, Codex/OpenAI, GLM, MiniMax, Claude, and Gemini in parallel, optionally deliberate to consensus with a chaired vote, and get back one decided answer โ from the command line or any MCP-capable coding harness.
</div>
curl -fsSL https://roundtable.sh/install.sh | bash
Why Roundtable?
Every model has a blind spot it can't see. Right before an irreversible call โ an architecture, a migration, a rewrite โ is exactly when one model's confident answer deserves a second (and third, and fourth) opinion.
Roundtable convenes a panel of frontier models. Each answers independently; then, for
high-stakes calls, a multi-round deliberation lets every head read the whole table and
revise until a Claude chair declares CONSENSUS or names the remaining disagreement.
Disagreement is signal, not noise.
- ๐ณ๏ธ Advisory (default) โ every head answers once, blind to the others. Raw, independent reads.
- โ๏ธ Deliberation (
--rounds N) โ heads see each other and revise; a neutral chair rulesCONSENSUS/CONTINUEand stops early on agreement. - ๐ API keys are enough โ no local CLIs required. Missing heads are skipped; the council runs on whatever subset you've configured.
- ๐ฆ One binary, everywhere โ a CLI, an MCP server, and a one-command installer that wires itself into your coding harness.
Example
$ roundtable "Reply with exactly: OK three words" --heads claude,gemini
# ๐ช Round Table โ 2 heads โ advisory
## ๐ต Claude (claude-opus-4-8, Anthropic) โ OK three words
## โจ Gemini (gemini-3.1-pro-preview, Google) โ OK three words
Add --rounds 3 and the heads deliberate; a chair prints VERDICT: CONSENSUS (or
CONTINUE) with the points they agreed on and any dissent named.
Install
curl -fsSL https://roundtable.sh/install.sh | bash
Or pick your package manager โ all four deliver the same engine:
pip install roundtable
uv tool install roundtable
brew install frontier-infra/tap/roundtable
The installer places the engine under ${XDG_DATA_HOME:-~/.local/share}/roundtable,
symlinks roundtable into ~/.local/bin, and prints a PATH hint if needed.
Quickstart
# 1. Configure keys (masked prompts; shows which heads are โ/โ). Stored chmod-600
# in ~/.config/roundtable/config.env. Any subset works โ missing heads are skipped.
roundtable auth
# 2. Ask the council
roundtable "Postgres or SQLite for a single-tenant internal tool?"
# 3. Deliberate to consensus on a high-stakes call
roundtable ask -q "Should we rewrite the billing service in Go?" --rounds 3
roundtable doctor shows which heads are configured and pings each for reachability.
Flags
-q/--question ยท -c/--context <file> (shared background for every head) ยท
--heads grok,codex,openai,glm,minimax,claude,gemini ยท --rounds N (deliberation) ยท
--research (web on, multi-step) ยท --timeout <secs> ยท --out <file>.
Exit 0 if at least one head answered.
The heads
| Head | Provider | Key / auth |
|---|---|---|
| ๐ค Grok | xAI | XAI_API_KEY (or local grok CLI / Hermes OAuth) |
| ๐ง Codex | OpenAI | local codex CLI (read-only) |
| ๐ง OpenAI | OpenAI | OPENAI_API_KEY (direct API โ no local CLI needed) |
| ๐ฃ GLM | Z.AI | ZAI_API_KEY |
| ๐ MiniMax | MiniMax | MINIMAX_API_KEY |
| ๐ต Claude | Anthropic | ANTHROPIC_API_KEY (also the deliberation chair) |
| โจ Gemini | GEMINI_API_KEY / GOOGLE_API_KEY |
Heads with no key/CLI are skipped inline โ the council runs on whatever subset you've configured, so API keys alone are enough (no local CLIs required).
MCP + wire into your harness
Roundtable ships an MCP server as a subcommand of the one binary:
roundtable mcp serve # stdio JSON-RPC; one tool: roundtable(question, heads?, rounds?, research?)
roundtable mcp config # prints the server JSON block to paste manually
Auto-wire detected harnesses (idempotent โ backs up first, never clobbers):
roundtable install # detect + wire everything present
roundtable install --harness cursor,codex
roundtable install --all # non-interactive
Wires Claude Code (skill + MCP), Cursor (~/.cursor/mcp.json),
Codex CLI (~/.codex/config.toml), and prints a generic JSON block for anything else:
{ "command": "roundtable", "args": ["mcp", "serve"] }
Use in Claude Code
Roundtable ships as a Claude Code plugin โ a roundtable skill that drives the CLI.
Two ways to add it:
A โ Plugin marketplace (inside Claude Code):
/plugin marketplace add frontier-infra/roundtable
/plugin install roundtable@roundtable
The skill calls the globally-installed roundtable CLI, so install that first:
curl -fsSL https://roundtable.sh/install.sh | bash.
B โ roundtable install โ auto-wires the skill and the MCP server into Claude
Code (plus Cursor / Codex) in one step:
roundtable install
Commands
roundtable "question" shorthand for `ask`
roundtable ask run the council (all engine flags)
roundtable auth [provider] configure API keys (masked, chmod-600)
roundtable models per-head model picker
roundtable heads enable/disable heads
roundtable doctor which heads are configured + reachability ping
roundtable config show / edit config.env
roundtable mcp serve|config MCP stdio server / print config
roundtable install auto-wire detected harnesses
roundtable version | update show version / upgrade in place
For agents
Building on top of Roundtable? See AGENTS.md โ a concise guide for an
AI agent to install, configure, run, and wire Roundtable into its own harness.
Links
- Website & docs โ https://roundtable.sh
- Source โ https://github.com/frontier-infra/roundtable
- Frontier Infra โ https://frontierinfra.org
License
MIT ยฉ Frontier Infra
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.