Persistent local knowledge for AI coding agents with structured records, search, and DOT context.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Persistent knowledge base tools for Claude Code.
Claude remembers your projects, decisions, and patterns across sessions β stored on your machine, no cloud required.
Built by AIM Studio Β· Free Β· MIT License
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.
Kilonova gives Claude a persistent knowledge base on your local machine. At session start, Claude loads your DOT (Document of Truth) β 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.
Or from source:
Add to ~/.claude/settings.json:
Copy CLAUDE.md.template to ~/.claude/CLAUDE.md (or append to your existing one).
1. Create your first KB topic:
In Claude Code, just start writing:
2. Load it next session:
3. Search it:
A DOT is a plain text file with three sections:
Symbols 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.
claude_contextCopy schemas/claude_context/ into your KB directory under <kb_root>/claude_context/schemas/:
| Entity type | Use for |
|---|---|
project_state | Current status, location, next action per project |
decision | Architectural choices with rationale |
pattern | Code conventions, gotchas, file locations |
active_task | In-flight work across sessions |
session_note | End-of-session summaries |
| Tool | Description |
|---|---|
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 |
Kilonova doesn't care what you store. Define your own schemas:
Then write records to it and search them naturally.
Kilonova MCP is the free, standalone KB layer extracted from Milna OS β 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 Β· Β© AIM Studio
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/kilonova-mcp)<a href="https://allmcps.com/mcp/kilonova-mcp"><img src="https://allmcps.com/api/badge/kilonova-mcp?style=directory" alt="Kilonova MCP on AllMCPs" /></a>