Kilonova MCP

io.github.MilnaOS由 GitHub 账号 MilnaOS 发布v0.1.1更新于 Oct 24, 2026

Persistent local knowledge for AI coding agents with structured records, search, and DOT context.

已验证STDIO仅桌面知识与记忆开发者工具

概览

AI 生成的概览

面向 AI 编程助手的本地文件式知识库:以结构化记录保存项目状态、决策与模式,并在后续会话中重新载入。

可以做什么
  • 载入 DOT(事实文档)参考文档到上下文,并借助目录只取所需章节
  • 按主题、实体类型和名称搜索、写入与读取结构化记录,写入时与已有记录合并
  • 列出知识库主题及记录数量,并查看某实体类型的字段结构
  • 查看知识库大小与记录统计,并可将知识库镜像备份到 OneDrive(支持试运行)
适用场景
适合在同一个项目上跨多次会话使用编程助手,希望决策、约定和进行中的任务得以保留、不必每次重新说明的场景。也适合希望以自定义结构在本地保存项目知识、不依赖云服务的团队。
运行要求
作为本地 Python 进程运行,从 PyPI 安装(pip install kilonova-mcp),通过 python -m kilonova_mcp 启动。需要一个知识库目录,由环境变量 KILONOVA_KB_ROOT 指定或使用平台默认路径。起始 schema 与 CLAUDE.md 模板需手动复制。仅支持桌面端。
安装前请注意
助手可以写入和更新知识库记录,存储内容会随之变化,建议留意保存了什么。备份工具会把知识库镜像到 OneDrive,即将本地项目笔记复制到第三方云服务。知识库可能包含内部架构与决策,请将 KILONOVA_KB_ROOT 指向合适的位置。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kilonova MCP,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Kilonova MCP

Persistent knowledge base tools for Claude Code.
Claude remembers your projects, decisions, and patterns across sessions — stored on your machine, no cloud required.

Built by AIM Studio · Free · MIT License


The Problem

Every Claude Code session starts cold. You re-explain your project structure, re-describe decisions you made last week, re-state what's in flight. Context burns fast.

The Solution: DOT + KB

Kilonova gives Claude a persistent knowledge base on your local machine. At session start, Claude loads your DOT (Document of Truth) — a compressed, structured reference doc with your project state, active tasks, decisions, and patterns. During the session, Claude writes new discoveries back to the KB. Next session, it's all there.

Session 1: Claude learns your architecture → kb_write saves the decisionSession 2: dot_load → Claude already knows. No recap needed.

Install

bash
pip install kilonova-mcp

Or from source:

bash
git clone https://github.com/MilnaOS/kilonova-mcpcd kilonova-mcppip install -e .

Wire Up Claude Code

Add to ~/.claude/settings.json:

json
{  "mcpServers": {    "kilonova": {      "command": "python",      "args": ["-m", "kilonova_mcp"],      "env": {        "KILONOVA_KB_ROOT": "/path/to/your/kb"      }    }  }}

Copy CLAUDE.md.template to ~/.claude/CLAUDE.md (or append to your existing one).

Quick Start

1. Create your first KB topic:

In Claude Code, just start writing:

mcp__kilonova__kb_write(  topic="claude_context",  entity_type="project_state",  name="my-project",  data={    "name": "my-project",    "status": "active",    "location": "/path/to/project",    "summary": "What this project is",    "next_action": "What to do next"  })

2. Load it next session:

mcp__kilonova__dot_load(topic="claude_context")

3. Search it:

mcp__kilonova__kb_search(topic="claude_context", query="authentication decision")

The DOT Format

A DOT is a plain text file with two sections:

---TOC---1:Projects|1.1:My_Project2:Active_Tasks3:Decisions
---CARDS---
## [1] PROJECTS### [1.1] My ProjectSTATUS: activeNEXT: wire up the auth flow

The TOC lets Claude fetch only the section it needs. Cards hold the actual content.

See example_dot/ for a starter template.


Starter Schema: claude_context

Copy schemas/claude_context/ into your KB directory under <kb_root>/claude_context/schemas/:

Entity typeUse for
project_stateCurrent status, location, next action per project
decisionArchitectural choices with rationale
patternCode conventions, gotchas, file locations
active_taskIn-flight work across sessions
session_noteEnd-of-session summaries

Tools

ToolDescription
dot_load(topic)Load full DOT document into context
kb_search(topic, query)Search records by natural language query
kb_write(topic, entity_type, name, data)Write/update a record (merges with existing)
kb_load(topic, entity_type, name)Load one specific record
kb_topics()List all KB topics and record counts
kb_schema(topic, entity_type?)Show field schema for an entity type
corpus_status(topic)Show KB size and record counts
kb_backup(dry?)Mirror KB to OneDrive

Bring Your Own KB

Kilonova doesn't care what you store. Define your own schemas:

json
// kb/my_topic/schemas/component.json{  "name": {"type": "string", "description": "Component name"},  "file": {"type": "string", "description": "Path to file"},  "purpose": {"type": "string", "description": "What it does"},  "dependencies": {"type": "array", "description": "What it depends on"}}

Then write records to it and search them naturally.


Part of the Kilonova Ecosystem

Kilonova MCP is the free, standalone KB layer extracted from Milna OS — a full BYOK multi-model AI terminal. If you want the whole thing (parallel model legs, distillation engine, web ingestion, local+cloud hybrid inference), check out Milna OS.


MIT License · © AIM Studio

来源:README.md,提交 ccb7767

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分