# karve

> Use this tool when you need to store and retrieve contextual information across sessions without relying on cloud services. Karve provides persistent semantic memory for Claude Code, enabling efficient context storage and retrieval through local embeddings and six MCP tools. It solves problems of data persistence and session continuity, accepting code inputs and outputting stored context for seamless session management.

Canonical page: https://skillsregistry.net/skills/cspenn-karve  
JSON: https://api.skillsregistry.net/v1/skills/cspenn-karve

## Description

Provides persistent semantic memory for Claude Code via local embeddings and six MCP tools, enabling context storage and retrieval across sessions without cloud dependencies.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/gxdo5co799)
- **Repository:** <https://github.com/cspenn/karve>

## 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": "cspenn-karve"
    }
  }
}
```

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