# Kimi Memory

> Use this tool when you need to enhance AI assistants with persistent knowledge-base capabilities, solving problems of knowledge retention and retrieval in natural language interactions. It takes in files and raw content as inputs, and outputs a searchable, AI-structured memory base, ideal for applications requiring intelligent information storage and recall. Utilize Kimi Memory in contexts where AI assistants need to learn from and recall large amounts of information, such as virtual customer support or data-intensive research tasks.

Canonical page: https://skillsregistry.net/skills/sarpixelpioneer-kimi-memory  
JSON: https://api.skillsregistry.net/v1/skills/sarpixelpioneer-kimi-memory

## Description

Intelligent memory system providing persistent knowledge-base capabilities for AI assistants. Uses ChromaDB for vector storage, Ollama for local embeddings (bge-m3 model), and DeepSeek for AI-powered document preprocessing. Supports learning from files, natural language memory search, and hybrid storage of raw and AI-structured content.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sarpixelpioneer-kimi-memory)
- **Repository:** <https://github.com/sarpixelpioneer/kimi-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": "sarpixelpioneer-kimi-memory"
    }
  }
}
```

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