Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Durable symmetric deliberation between two AI agents, with isolated worktrees and peer review.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
作者没有在注册中心列出安装信息。请查看下方作者的 README。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 naruminho 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.2.0)于2个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Systemdox
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Durable, symmetric deliberation between two AI agents — with isolated git worktrees, peer review, automated validation, and an explicit approval workflow.
Synod started life as the "council" inside a personal AI infrastructure where two autonomous agents (an orchestrator and an executor) needed to make *real* decisions and *real* code changes together — without one of them silently becoming the other's rubber stamp.
Most multi-agent frameworks are orchestration theater: one agent calls another as a tool and calls the output "collaboration". Synod is built around a different premise — two agents that are peers by construction:
plan, review, synthesize, ratify, ...). A crashed run leaves an inspectable trail, not a mystery.main; a human-facing approval step stands between "looks done" and "published".pipx install synod-council
Or from source:
git clone https://github.com/naruminho/synod-council
cd synod && pip install .
from synod.deliberation import Deliberator, Store, HTTPAdapter
adapters = { "Alice": HTTPAdapter("Alice", "http://127.0.0.1:9001/ask"), "Bob": HTTPAdapter("Bob", "http://127.0.0.1:9002/ask"), } synod = Deliberator(adapters, Store("council.db")) result = synod.run("Should we use SQLite or Postgres for this workload?", initiator="Alice") print(result.decision, result.confidence, result.status) # consensus | reconciled
Synod ships an MCP server so any MCP-capable client (Claude Desktop, Claude Code, Cursor, ...) can start a deliberation:
synod-mcp # stdio transport
Add it to your client config and ask your agents to *deliberate* instead of guessing.
synod-server --port 8790
curl -X POST http://127.0.0.1:8790/run -d '{"problem": "...", "initiator": "Alice"}'
plan (parallel) → cross-review (parallel) → synthesis → [ratification → reconciliation?]
If reviewers raise unresolved blockers, or confidence lands below 0.7, the candidate decision goes to ratification by the non-synthesizing peer; a rejection forces explicit reconciliation instead of silent consensus.
Extracted and battle-tested from a production personal infrastructure where it has been deciding architecture and shipping code since 2026. The two-agent design is intentional; N-participant support is on the roadmap.
MIT