# kimi-mem

> kimi-mem — skywalker-35-kimi-mem. Use this tool when you need to enhance your Kimi Code CLI with persistent memory capabilities, such as auto-capturing and semantic vector search, to improve code management and discovery. It solves problems related to code organization and retrieval, allowing for efficient searching and learning of user profiles. Ideal for use in git-based development workflows, it provides a Web UI for intuitive interaction and management of captured code memories.

Canonical page: https://skillsregistry.net/skills/skywalker-35-kimi-mem  
JSON: https://api.skillsregistry.net/v1/skills/skywalker-35-kimi-mem

## Description

Persistent memory plugin for Kimi Code CLI — auto-capture, semantic vector search, user profile learning, Web UI. Port of opencode-mem. Kimi Code 持久记忆插件。

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/skywalker-35/kimi-mem)

## 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": "skywalker-35-kimi-mem"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/skywalker-35-kimi-mem` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/skywalker-35-kimi-mem/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