Kilonova MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kilonova MCPSave my active tasks and decisions for this session."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: xtage
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 decision
Session 2: dot_load → Claude already knows. No recap needed.Install
pip install kilonova-mcpOr from source:
git clone https://github.com/MilnaOS/kilonova-mcp
cd kilonova-mcp
pip install -e .Wire Up Claude Code
Add to ~/.claude/settings.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 three sections:
---SYMBOLS---
[PR]=My Project (/path/to/project)
[DB]=Database (PostgreSQL on localhost:5432)
---TOC---
1:Projects|1.1:My_Project
2:Active_Tasks
3:Decisions
---CARDS---
## [1] PROJECTS
### [1.1] My Project
STATUS: active
NEXT: wire up the auth flowSymbols compress repeated references. 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 type | Use for |
| Current status, location, next action per project |
| Architectural choices with rationale |
| Code conventions, gotchas, file locations |
| In-flight work across sessions |
| End-of-session summaries |
Tools
Tool | Description |
| Load full DOT document into context |
| Search records by natural language query |
| Write/update a record (merges with existing) |
| Load one specific record |
| List all KB topics and record counts |
| Show field schema for an entity type |
| Show KB size and record counts |
| Mirror KB to OneDrive |
Bring Your Own KB
Kilonova doesn't care what you store. Define your own schemas:
// 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
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
Persistent, governed institutional memory for Claude Code — specs, decisions, learnings.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenancePersistent project memory + architectural decisions + pre-execution safety hooks for Claude Code. Local-only storage, multi-repo workspace, automatic knowledge extraction via background auditor.2814MIT
- AlicenseNot gradedqualityBmaintenanceProvides Claude with persistent, semantic knowledge of a codebase across sessions by maintaining a local knowledge base of structural maps, compressed file summaries, and insights.71MIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent, searchable memory for Claude Code using local SQLite, semantic embeddings, and full-text search, enabling Claude to recall and retrieve context across sessions and projects without external services.64MIT
- FlicenseNot gradedqualityDmaintenanceProvides persistent semantic memory for Claude Code via local embeddings and six MCP tools, enabling context storage and retrieval across sessions without cloud dependencies.-