# lake-of-embeddings

> Use this tool when you need to search and retrieve specific information from your personal knowledge bases, such as Obsidian notes, SQLite databases, and plaintext files. It solves problems of information overload and disorganization by indexing and exposing your data via a local semantic search interface. Ideal for use cases where you need to quickly find relevant information within your own data repositories.

Canonical page: https://skillsregistry.net/skills/tungpun-lake-of-embeddings  
JSON: https://api.skillsregistry.net/v1/skills/tungpun-lake-of-embeddings

## Description

Local semantic search over your personal knowledge bases. Index Obsidian notes, SQLite databases, and plaintext files into ChromaDB, exposed to Claude via an MCP server.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/tungpun/lake-of-embeddings)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "tungpun-lake-of-embeddings"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tungpun-lake-of-embeddings` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tungpun-lake-of-embeddings/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt