asdecided-core
Provides deterministic, read-only access to engineering decisions, requirements, and designs stored as Markdown in a repository, enabling agents to retrieve and follow decided context without embeddings or external services.
README
AsDecided
Engineering decisions your agents can follow. Build, as decided.
AsDecided keeps requirements, decisions, designs, roadmaps, and prompts as typed Markdown in your repository. Its native Rust engine validates that knowledge, retrieves relevant decisions deterministically, and serves it read-only to agents over MCP.
No embeddings, model call, hosted index, or Python runtime is required. The same repository state produces the same answer.
Install
Install the native engine and MCP server through Homebrew:
brew install asdecided/tap/asdecided-core
Rust users can install the decided CLI directly from crates.io:
cargo install decided
cargo install decided-mcp
Windows users can install both native executables through Scoop:
scoop bucket add asdecided https://github.com/asdecided/scoop-bucket
scoop install asdecided
Native decided and decided-mcp archives are also published on
GitHub Releases.
rac-core is no longer distributed through PyPI. Python API consumers should
use asdecided/sdk, which is a
client SDK rather than a second engine implementation.
Start a repository
decided quickstart
decided validate decisions/
decided gate decisions/
decided gate decisions/ --code --base origin/main
New repositories use:
.decided/config.yaml
decisions/
Existing artifact IDs such as RAC-ABC123DEF456 are durable identities and do
not change with the product name.
Migrate an existing repository
Migration is explicit and never runs during an ordinary command:
decided migrate layout . --dry-run
decided migrate layout .
The migration moves .rac/ to .decided/ and rac/ to decisions/. It
refuses to overwrite either destination.
MCP
The official MCP Registry identity is io.github.asdecided/core.
{
"mcpServers": {
"asdecided": {
"command": "decided-mcp",
"args": ["--root", "."]
}
}
}
Architecture
Rust is the product engine and the only CLI/MCP runtime in this repository.
The authoritative language-neutral compatibility fixtures live in
asdecided-spec. Live-corpus validation is
based on validity, determinism, freshness, and cache/no-cache equality.
Document ingestion remains an ancillary Python connector rather than part of
the core engine. The retired Python engine is preserved for historical review
at the immutable
python-engine-final
tag; it is not maintained or run in normal CI.
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。