# RobotMem

> Use this tool when you need to equip physical robots and AI agents with a persistent memory system that enables learning, recall, and updating of information. RobotMem solves problems related to information retrieval, storage, and management, supporting various use cases such as robotics applications and offline operation. It takes in perceptions, updates, and queries as inputs and outputs relevant information, making it ideal for scenarios where model-agnostic and efficient memory management is required.

Canonical page: https://skillsregistry.net/skills/robotmem  
JSON: https://api.skillsregistry.net/v1/skills/robotmem

## Description

Model-agnostic persistent memory system designed for physical robots and AI agents. Provides seven core tools (learn, recall, save_perception, forget, update, start_session, end_session) combining BM25 full-text search with vector embeddings using reciprocal rank fusion. Supports spatial nearest-neighbor sorting for robotics applications, CJK language tokenization, structured JSON filtering, and local SQLite storage with optional ONNX models for offline operation.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-02

## Source

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

## 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": "robotmem"
    }
  }
}
```

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