# memex

> memex — vndee-memex. Use this tool when you need to create a local, self-contained knowledge graph for AI agents, enabling hybrid search and temporal memory capabilities without requiring API keys. It solves problems related to data storage, retrieval, and management for AI applications, providing a single Go binary and SQLite interface for seamless integration. Ideal for use cases where local data control and flexibility are essential, such as development, testing, or offline environments.

Canonical page: https://skillsregistry.net/skills/vndee-memex  
JSON: https://api.skillsregistry.net/v1/skills/vndee-memex

## Description

Local-first temporal knowledge graph memory for AI agents. Runs with Ollama — no API keys required. Single Go binary + SQLite. Hybrid search, MCP server, REST API, interactive TUI.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** database
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/vndee/memex)

## 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": "vndee-memex"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vndee-memex` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vndee-memex/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