Вече — MCP 서버로 다중 시약 분리.

veche는 오케스트라 에이전트 (Claude 코드, 사용자 정의 에이전트, 당신의 IDE) convene **committee 회의 ** LLM 에이전트와 읽기 사이 구조화 된 성적. 의정서는 각자 진화입니다: 각 일원은 안으로 replies 라운드, 누구나 리터럴 토큰 로 선택 할 수 있으며, 회의는 종료 순간 모두가 같은 라운드에서 전달 (또는 max_rounds]).

이름은 medieval Slavic вече에서 옵니다. 문제가 해결되었을 때 acclamation 및 분산. 그 지도는 거의 직접 위에 rounds + until silence.

v1는 2개의 비대칭 CLI 역행 접합기를 발송합니다:

-Codex 를 통해 codex exec (OpenAI)

• Claude Code 를 통해 claude -p (Anthropic) - 아이를 막는 반복 감시 이 같은 서버에서 Claude Code

관현관은 Claude Code가 될 수 있습니다. Claude Code ↔ another Claude Code + Codex위원회. 건축과 행동은 C4-inspired 4 레벨 모델을 사용하여 spec/에 완전히 지정; 코드는 다음과 같습니다 spec와 변화는 spec에 첫째로 합니다.

---

왜

Veche

Вече — bounded multi-agent deliberation as an MCP server.

veche is a Model Context Protocol (MCP) server that lets an orchestrator agent (Claude Code, a custom agent, your IDE) convene committee meetings between LLM agents and read back a structured transcript. The protocol is self-extinguishing: every member replies in rounds, anyone can opt out with the literal token ``, and the meeting terminates the moment everyone passes in the same round (or hits max_rounds).

The name comes from the medieval Slavic вече — a popular assembly that deliberated by acclamation and dispersed when the matter was settled. That maps almost directly onto rounds + until silence.

v1 ships two symmetric CLI-backed adapters:

• Codex via codex exec (OpenAI)
• Claude Code via claude -p (Anthropic) — with a recursion guard that prevents a child Claude Code from re-entering this same server

The orchestrator may itself be Claude Code, enabling Claude Code ↔ another Claude Code + Codex committees. Architecture and behaviour are fully specified in spec/ using a C4-inspired four-level model; code follows the spec and changes are made to the spec first.

---

Why

LLMs collapse into a single line of reasoning on hard problems. A standing MCP tool for pulling a second opinion from a different model — or a differently-prompted instance of the same model — broadens the search, surfaces blind spots, and produces more balanced decisions. The committee protocol drives the discussion to a stable point without the orchestrator hand-rolling turn-taking.

Install

npm install -g veche
veche install        # writes SKILL.md to ~/.claude/skills/veche/ and ~/.codex/skills/veche/
                     # plus optional skill UI metadata under agents/openai.yaml
                     # plus claude mcp add / codex mcp add for the stdio MCP server

veche install --for=hermes   # opt-in install into Hermes Agent (~/.hermes/skills/veche/
                             # plus `hermes mcp add veche --command node --args …`)

Restart your Claude Code / Codex / Hermes Agent session after installing. The skill is invoked as /veche .

If you cloned the repo:

npm install
npm run build
node dist/bin/veche.js install

Prerequisites

Quick start

As a Claude Code skill

After veche install, open Claude Code and type:

/veche should we use argparse or click for a new Python CLI?

The skill first asks for launch options: whether to include a Human Participant, whether