# Mnemic

> Use this tool when you need to provide coding agents with a shared, auditable, and graph-backed long-term memory layer to store and recall knowledge. It solves problems related to data consistency, transparency, and explainability by offering features like write preview, temporal recall, and provenance explanations. Ideal for use cases requiring reliable and traceable memory management, Mnemic accepts knowledge inputs and outputs recalled information with accompanying explanations.

Canonical page: https://skillsregistry.net/skills/dongtang3-mnemic  
JSON: https://api.skillsregistry.net/v1/skills/dongtang3-mnemic

## Description

Local-first memory kernel for coding agents that provides a shared, auditable, graph-backed long-term memory layer with features like write preview, temporal recall, and provenance explanations.

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/y4xh60l3zk)
- **Repository:** <https://github.com/dongtang3/mnemic>

## 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": "dongtang3-mnemic"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dongtang3-mnemic` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dongtang3-mnemic/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