# Local Memory

> Use this tool when you need to store and retrieve local memories for AI agents, enabling persistent memory across conversations without relying on external cloud services. It solves problems of data persistence and retrieval, providing features like semantic search and automatic relevance scoring for efficient memory management. The tool takes in vector embeddings and metadata as inputs and outputs retrieved memories, making it ideal for use cases requiring autonomous decision-making and personalized interactions.

Canonical page: https://skillsregistry.net/skills/basst85-local-memory  
JSON: https://api.skillsregistry.net/v1/skills/basst85-local-memory

## Description

Provides local memory storage and retrieval for AI agents using vector embeddings generated by Ollama models. Stores memories as vectors in a Zvec database with metadata including workspace keys, memory types (decisions, preferences, facts, etc.), importance scores, and timestamps. Features semantic search, memory superseding for updates, workspace isolation, and automatic relevance scoring based on embedding similarity and importance weights. Designed for agents that need persistent memory across conversations without relying on external cloud services.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/basst85-local-memory)
- **Repository:** <https://github.com/basst85/local-memory-mcp>

## 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": "basst85-local-memory"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/basst85-local-memory` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/basst85-local-memory/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