# VLS-32M-Context-Local-LLM

> VLS-32M-Context-Local-LLM — veloresearch-vls-32m-context-local-llm. Use this tool when you need to run large language models with extended context locally on your machine, solving problems like limited window size and cloud dependency. It provides a local LLM server that accepts code inputs and returns outputs based on GGUF models, all within a 32M-token memory. Ideal for use cases requiring secure, self-contained, and high-capacity language processing, such as coding and development tasks.

Canonical page: https://skillsregistry.net/skills/veloresearch-vls-32m-context-local-llm  
JSON: https://api.skillsregistry.net/v1/skills/veloresearch-vls-32m-context-local-llm

## Description

Give Claude Code, Codex and opencode a 32M-token memory that never leaves your machine. Local LLM server (MCP + OpenAI API) that runs any GGUF model with a context far larger than its window - no cloud, no retraining, no vector database. Windows and Linux, one command.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/Veloresearch/VLS-32M-Context-Local-LLM)

## 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": "veloresearch-vls-32m-context-local-llm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/veloresearch-vls-32m-context-local-llm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/veloresearch-vls-32m-context-local-llm/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